{
  "generatedAt": "2026-11-21T19:54:46.577Z",
  "syncMeta": {
    "lastSyncAt": "2026-11-21T19:54:45.261Z",
    "source": "openrouter",
    "status": "ok",
    "modelCount": 374,
    "providerCount": 59,
    "aiBotsCount": 60,
    "aiBotsAdded": 0,
    "eventsAdded": 0,
    "removedCount": 0,
    "durationMs": 471
  },
  "count": 374,
  "models": [
    {
      "id": "baidu/ernie-5.5-flash-preview:free",
      "slug": "baidu-ernie-5-5-flash-preview-free",
      "name": "Baidu: ERNIE-5.5-Flash-Preview (free)",
      "provider": "baidu",
      "providerName": "Baidu",
      "description": "ERNIE 5.5 Flash Preview is the latest foundation model in the ERNIE family, with comprehensive improvements in coding, agentic capabilities, knowledge work, and deep research. It has 280 billion total...",
      "inputPer1M": 0,
      "outputPer1M": 0,
      "blendedPer1M": 0,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1024000,
      "maxCompletionTokens": 921600,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": true,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "free",
      "createdAt": "2026-11-10",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openrouter/free",
      "slug": "openrouter-free",
      "name": "Free Models Router",
      "provider": "openrouter",
      "providerName": "Openrouter",
      "description": "The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...",
      "inputPer1M": 0,
      "outputPer1M": 0,
      "blendedPer1M": 0,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 200000,
      "maxCompletionTokens": null,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": true,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "free",
      "createdAt": "2026-02-01",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemma-4-26b-a4b-it:free",
      "slug": "google-gemma-4-26b-a4b-it-free",
      "name": "Google: Gemma 4 26B A4B  (free)",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...",
      "inputPer1M": 0,
      "outputPer1M": 0,
      "blendedPer1M": 0,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 32768,
      "inputModalities": [
        "image",
        "text",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": true,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "free",
      "createdAt": "2026-04-03",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemma-4-31b-it:free",
      "slug": "google-gemma-4-31b-it-free",
      "name": "Google: Gemma 4 31B (free)",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...",
      "inputPer1M": 0,
      "outputPer1M": 0,
      "blendedPer1M": 0,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 32768,
      "inputModalities": [
        "image",
        "text",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": true,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "free",
      "createdAt": "2026-04-02",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "inclusionai/ling-3.2-flash:free",
      "slug": "inclusionai-ling-3-2-flash-free",
      "name": "inclusionAI: Ling 3.2 Flash (free)",
      "provider": "inclusionai",
      "providerName": "Inclusionai",
      "description": "Ling 3.2 Flash is a hybrid reasoning model from inclusionAI that accepts text and image input, with a 1M-token context window and up to 200 images per request. Thinking can...",
      "inputPer1M": 0,
      "outputPer1M": 0,
      "blendedPer1M": 0,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 262144,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": true,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "free",
      "createdAt": "2026-11-13",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "liquid/lfm-3-1.7b:free",
      "slug": "liquid-lfm-3-1-7b-free",
      "name": "LiquidAI: LFM3-1.7B (free)",
      "provider": "liquid",
      "providerName": "Liquid",
      "description": "A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used...",
      "inputPer1M": 0,
      "outputPer1M": 0,
      "blendedPer1M": 0,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 8192,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": true,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "free",
      "createdAt": "2026-11-06",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
      "slug": "nvidia-nemotron-3-nano-omni-30b-a3b-reasoning-free",
      "name": "NVIDIA: Nemotron 3 Nano Omni (free)",
      "provider": "nvidia",
      "providerName": "NVIDIA",
      "description": "NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...",
      "inputPer1M": 0,
      "outputPer1M": 0,
      "blendedPer1M": 0,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 256000,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "audio",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": true,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "free",
      "createdAt": "2026-04-28",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "nvidia/nemotron-3-ultra-550b-a55b:free",
      "slug": "nvidia-nemotron-3-ultra-550b-a55b-free",
      "name": "NVIDIA: Nemotron 3 Ultra (free)",
      "provider": "nvidia",
      "providerName": "NVIDIA",
      "description": "NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...",
      "inputPer1M": 0,
      "outputPer1M": 0,
      "blendedPer1M": 0,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": true,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "free",
      "createdAt": "2026-06-04",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "nvidia/nemotron-3.5-lightning:free",
      "slug": "nvidia-nemotron-3-5-lightning-free",
      "name": "NVIDIA: Nemotron 3.5 Lightning (free)",
      "provider": "nvidia",
      "providerName": "NVIDIA",
      "description": "NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...",
      "inputPer1M": 0,
      "outputPer1M": 0,
      "blendedPer1M": 0,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": true,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "free",
      "createdAt": "2026-08-11",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "nvidia/nemotron-3.5-super-vl:free",
      "slug": "nvidia-nemotron-3-5-super-vl-free",
      "name": "NVIDIA: Nemotron 3.5 Super VL (free)",
      "provider": "nvidia",
      "providerName": "NVIDIA",
      "description": "NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...",
      "inputPer1M": 0,
      "outputPer1M": 0,
      "blendedPer1M": 0,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": true,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "free",
      "createdAt": "2026-10-15",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "particle-ai/particle-1:free",
      "slug": "particle-ai-particle-1-free",
      "name": "Particle AI: Particle-1 (free)",
      "provider": "particle-ai",
      "providerName": "Particle Ai",
      "description": "Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data...",
      "inputPer1M": 0,
      "outputPer1M": 0,
      "blendedPer1M": 0,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": true,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "free",
      "createdAt": "2026-10-28",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "recursive/flint-v1.0:free",
      "slug": "recursive-flint-v1-0-free",
      "name": "Recursive: Flint (free)",
      "provider": "recursive",
      "providerName": "Recursive",
      "description": "Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited...",
      "inputPer1M": 0,
      "outputPer1M": 0,
      "blendedPer1M": 0,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": true,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "free",
      "createdAt": "2026-10-21",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "inclusionai/ling-3.0-tiny",
      "slug": "inclusionai-ling-3-0-tiny",
      "name": "inclusionAI: Ling 3.0 Tiny",
      "provider": "inclusionai",
      "providerName": "Inclusionai",
      "description": "Ling 3.0 Tiny is a mixture-of-experts model from InclusionAI, with 1.3B active parameters out of 7.9B total. It is designed for responsive agents, instruction following, and multi-turn conversations, with switchable...",
      "inputPer1M": 0.015,
      "outputPer1M": 0.045,
      "blendedPer1M": 0.0225,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 250000,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-08-06",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "meta-llama/llama-3.1-8b-instruct",
      "slug": "meta-llama-llama-3-1-8b-instruct",
      "name": "Meta: Llama 3.1 8B Instruct",
      "provider": "meta-llama",
      "providerName": "Meta Llama",
      "description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...",
      "inputPer1M": 0.02,
      "outputPer1M": 0.04,
      "blendedPer1M": 0.025,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2024-07-23",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/mistral-nemo",
      "slug": "mistralai-mistral-nemo",
      "name": "Mistral: Mistral Nemo",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...",
      "inputPer1M": 0.029,
      "outputPer1M": 0.03,
      "blendedPer1M": 0.0293,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2024-07-19",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "scaledown/extract",
      "slug": "scaledown-extract",
      "name": "ScaleDown: Extract",
      "provider": "scaledown",
      "providerName": "Scaledown",
      "description": "Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the...",
      "inputPer1M": 0.04,
      "outputPer1M": 0,
      "blendedPer1M": 0.03,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 900000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-10-13",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "scaledown/summarize",
      "slug": "scaledown-summarize",
      "name": "ScaleDown: Summarize",
      "provider": "scaledown",
      "providerName": "Scaledown",
      "description": "Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...",
      "inputPer1M": 0.04,
      "outputPer1M": 0,
      "blendedPer1M": 0.03,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 4000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-10-13",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "inclusionai/ling-3.0-flash",
      "slug": "inclusionai-ling-3-0-flash",
      "name": "inclusionAI: Ling 3.0 Flash",
      "provider": "inclusionai",
      "providerName": "Inclusionai",
      "description": "*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...",
      "inputPer1M": 0.021,
      "outputPer1M": 0.063,
      "blendedPer1M": 0.0315,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 32768,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-07-23",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-oss-20b",
      "slug": "openai-gpt-oss-20b",
      "name": "OpenAI: gpt-oss-20b",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...",
      "inputPer1M": 0.017,
      "outputPer1M": 0.085,
      "blendedPer1M": 0.034,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 117964,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-08-05",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "sao10k/l3-lunaris-8b",
      "slug": "sao10k-l3-lunaris-8b",
      "name": "Sao10K: Llama 3 8B Lunaris",
      "provider": "sao10k",
      "providerName": "Sao10k",
      "description": "Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....",
      "inputPer1M": 0.04,
      "outputPer1M": 0.05,
      "blendedPer1M": 0.0425,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 8192,
      "maxCompletionTokens": 7372,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2024-08-13",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "nex-agi/nex-n2.5-mini",
      "slug": "nex-agi-nex-n2-5-mini",
      "name": "Nex AGI: Nex-N2.5-Mini",
      "provider": "nex-agi",
      "providerName": "Nex Agi",
      "description": "Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...",
      "inputPer1M": 0.025,
      "outputPer1M": 0.1,
      "blendedPer1M": 0.0438,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-09-08",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "z-ai/glm-5.3-flash",
      "slug": "z-ai-glm-5-3-flash",
      "name": "Z.ai: GLM 5.3 Flash",
      "provider": "z-ai",
      "providerName": "Z Ai",
      "description": "GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...",
      "inputPer1M": 0.0399,
      "outputPer1M": 0.0784,
      "blendedPer1M": 0.0495,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-08-26",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "~z-ai/glm-flash-latest",
      "slug": "z-ai-glm-flash-latest",
      "name": "Z.ai: GLM Flash Latest",
      "provider": "z-ai",
      "providerName": "Z Ai",
      "description": "This model always redirects to the latest model in the GLM Flash family.",
      "inputPer1M": 0.0399,
      "outputPer1M": 0.0784,
      "blendedPer1M": 0.0495,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-08-27",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.7-flash",
      "slug": "qwen-qwen3-7-flash",
      "name": "Qwen: Qwen3.7 Flash",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...",
      "inputPer1M": 0.03,
      "outputPer1M": 0.13,
      "blendedPer1M": 0.055,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-07-27",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/mistral-small-24b-instruct-2501",
      "slug": "mistralai-mistral-small-24b-instruct-2501",
      "name": "Mistral: Mistral Small 3",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...",
      "inputPer1M": 0.05,
      "outputPer1M": 0.08,
      "blendedPer1M": 0.0575,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 32768,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-01-30",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "inference-net/schematron-v2-turbo",
      "slug": "inference-net-schematron-v2-turbo",
      "name": "Inference.net: Schematron V2 Turbo",
      "provider": "inference-net",
      "providerName": "Inference Net",
      "description": "Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...",
      "inputPer1M": 0.03,
      "outputPer1M": 0.15,
      "blendedPer1M": 0.06,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 8192,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-09-12",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "amazon/nova-micro-v1",
      "slug": "amazon-nova-micro-v1",
      "name": "Amazon: Nova Micro 1.0",
      "provider": "amazon",
      "providerName": "Amazon",
      "description": "Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...",
      "inputPer1M": 0.035,
      "outputPer1M": 0.14,
      "blendedPer1M": 0.0613,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 5120,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2024-12-05",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "tencent/hy4-flash",
      "slug": "tencent-hy4-flash",
      "name": "Tencent: Hy4 flash",
      "provider": "tencent",
      "providerName": "Tencent",
      "description": "Hy4 flash is a cost-efficient variant of [Hy4](https://openrouter.ai/tencent/hy4) from Tencent, served with roughly a quarter of the flagship's parameter count for lower latency and cost. It targets code assistance, agent...",
      "inputPer1M": 0.035,
      "outputPer1M": 0.1405,
      "blendedPer1M": 0.0614,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-11-16",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemma-3-4b-it",
      "slug": "google-gemma-3-4b-it",
      "name": "Google: Gemma 3 4B",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...",
      "inputPer1M": 0.05,
      "outputPer1M": 0.1,
      "blendedPer1M": 0.0625,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-03-13",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "cohere/command-r7b-12-2024",
      "slug": "cohere-command-r7b-12-2024",
      "name": "Cohere: Command R7B (12-2024)",
      "provider": "cohere",
      "providerName": "Cohere",
      "description": "Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...",
      "inputPer1M": 0.0375,
      "outputPer1M": 0.15,
      "blendedPer1M": 0.0656,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 4000,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2024-12-14",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "~deepseek/deepseek-v4-flash-latest",
      "slug": "deepseek-deepseek-v4-flash-latest",
      "name": "DeepSeek: DeepSeek V4 Flash Latest",
      "provider": "deepseek",
      "providerName": "DeepSeek",
      "description": "This model always redirects to the latest model in the DeepSeek V4 Flash family.",
      "inputPer1M": 0.044,
      "outputPer1M": 0.132,
      "blendedPer1M": 0.066,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-08-01",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemma-3-12b-it",
      "slug": "google-gemma-3-12b-it",
      "name": "Google: Gemma 3 12B",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...",
      "inputPer1M": 0.05,
      "outputPer1M": 0.15,
      "blendedPer1M": 0.075,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-03-13",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "tencent/hy-mt2-1.8b",
      "slug": "tencent-hy-mt2-1-8b",
      "name": "Tencent: Hy-MT2-1.8B",
      "provider": "tencent",
      "providerName": "Tencent",
      "description": "Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...",
      "inputPer1M": 0.044,
      "outputPer1M": 0.177,
      "blendedPer1M": 0.0773,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 8192,
      "maxCompletionTokens": 4096,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-08-20",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "ibm-granite/granite-4.2-8b",
      "slug": "ibm-granite-granite-4-2-8b",
      "name": "IBM: Granite 4.2 8B",
      "provider": "ibm-granite",
      "providerName": "Ibm Granite",
      "description": "Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...",
      "inputPer1M": 0.06,
      "outputPer1M": 0.15,
      "blendedPer1M": 0.0825,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 117964,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-08-31",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "deepseek/deepseek-v4.1-flash",
      "slug": "deepseek-deepseek-v4-1-flash",
      "name": "DeepSeek: DeepSeek V4.1 Flash",
      "provider": "deepseek",
      "providerName": "DeepSeek",
      "description": "DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...",
      "inputPer1M": 0.0498,
      "outputPer1M": 0.1992,
      "blendedPer1M": 0.0871,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 393216,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-09-10",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "microsoft/phi-4",
      "slug": "microsoft-phi-4",
      "name": "Microsoft: Phi 4",
      "provider": "microsoft",
      "providerName": "Microsoft",
      "description": "[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...",
      "inputPer1M": 0.07,
      "outputPer1M": 0.14,
      "blendedPer1M": 0.0875,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 16384,
      "maxCompletionTokens": 14745,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-01-10",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "gryphe/mythomax-l2-13b",
      "slug": "gryphe-mythomax-l2-13b",
      "name": "MythoMax 13B",
      "provider": "gryphe",
      "providerName": "Gryphe",
      "description": "One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge",
      "inputPer1M": 0.08,
      "outputPer1M": 0.11,
      "blendedPer1M": 0.0875,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 8192,
      "maxCompletionTokens": 3686,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2023-07-02",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "upstage/solar-mini4",
      "slug": "upstage-solar-mini4",
      "name": "Upstage: Solar Mini 4",
      "provider": "upstage",
      "providerName": "Upstage",
      "description": "Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...",
      "inputPer1M": 0.05,
      "outputPer1M": 0.2,
      "blendedPer1M": 0.0875,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 524288,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-09-23",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "inclusionai/ling-3.0-flash-vl",
      "slug": "inclusionai-ling-3-0-flash-vl",
      "name": "inclusionAI: Ling 3.0 Flash VL",
      "provider": "inclusionai",
      "providerName": "Inclusionai",
      "description": "Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...",
      "inputPer1M": 0.06,
      "outputPer1M": 0.18,
      "blendedPer1M": 0.09,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 32768,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-09-10",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "inclusionai/ling-3.1-flash",
      "slug": "inclusionai-ling-3-1-flash",
      "name": "inclusionAI: Ling 3.1 Flash",
      "provider": "inclusionai",
      "providerName": "Inclusionai",
      "description": "Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.",
      "inputPer1M": 0.06,
      "outputPer1M": 0.18,
      "blendedPer1M": 0.09,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 262144,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-10-02",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "prism-ml/ternary-bonsai-2-9b",
      "slug": "prism-ml-ternary-bonsai-2-9b",
      "name": "PrismML: Ternary Bonsai 2 9B",
      "provider": "prism-ml",
      "providerName": "Prism Ml",
      "description": "Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...",
      "inputPer1M": 0.08,
      "outputPer1M": 0.13,
      "blendedPer1M": 0.0925,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-10-16",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "inference-net/schematron-v2-small",
      "slug": "inference-net-schematron-v2-small",
      "name": "Inference.net: Schematron V2 Small",
      "provider": "inference-net",
      "providerName": "Inference Net",
      "description": "Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema...",
      "inputPer1M": 0.05,
      "outputPer1M": 0.23,
      "blendedPer1M": 0.095,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 8192,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-09-12",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/ministral-3b-2512",
      "slug": "mistralai-ministral-3b-2512",
      "name": "Mistral: Ministral 3 3B 2512",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.",
      "inputPer1M": 0.1,
      "outputPer1M": 0.1,
      "blendedPer1M": 0.1,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 104857,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-12-02",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "rekaai/reka-edge",
      "slug": "rekaai-reka-edge",
      "name": "Reka Edge",
      "provider": "rekaai",
      "providerName": "Rekaai",
      "description": "Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...",
      "inputPer1M": 0.1,
      "outputPer1M": 0.1,
      "blendedPer1M": 0.1,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 16384,
      "maxCompletionTokens": 14745,
      "inputModalities": [
        "image",
        "text",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-03-20",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "nvidia/nemotron-3.5-lightning",
      "slug": "nvidia-nemotron-3-5-lightning",
      "name": "NVIDIA: Nemotron 3.5 Lightning",
      "provider": "nvidia",
      "providerName": "NVIDIA",
      "description": "NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...",
      "inputPer1M": 0.07,
      "outputPer1M": 0.2,
      "blendedPer1M": 0.1025,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-08-11",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "amazon/nova-lite-v1",
      "slug": "amazon-nova-lite-v1",
      "name": "Amazon: Nova Lite 1.0",
      "provider": "amazon",
      "providerName": "Amazon",
      "description": "Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...",
      "inputPer1M": 0.06,
      "outputPer1M": 0.24,
      "blendedPer1M": 0.105,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 300000,
      "maxCompletionTokens": 5120,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2024-12-05",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "nvidia/nemotron-3-nano-30b-a3b",
      "slug": "nvidia-nemotron-3-nano-30b-a3b",
      "name": "NVIDIA: Nemotron 3 Nano 30B A3B",
      "provider": "nvidia",
      "providerName": "NVIDIA",
      "description": "NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...",
      "inputPer1M": 0.06,
      "outputPer1M": 0.24,
      "blendedPer1M": 0.105,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-12-14",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/mistral-small-3.2-24b-instruct",
      "slug": "mistralai-mistral-small-3-2-24b-instruct",
      "name": "Mistral: Mistral Small 3.2 24B",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...",
      "inputPer1M": 0.075,
      "outputPer1M": 0.2,
      "blendedPer1M": 0.1063,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 256000,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-06-20",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemma-4-26b-a4b-it",
      "slug": "google-gemma-4-26b-a4b-it",
      "name": "Google: Gemma 4 26B A4B",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...",
      "inputPer1M": 0.0675,
      "outputPer1M": 0.225,
      "blendedPer1M": 0.1069,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "image",
        "text",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-04-03",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "deepseek/deepseek-v4-flash-0731",
      "slug": "deepseek-deepseek-v4-flash-0731",
      "name": "DeepSeek: DeepSeek V4 Flash 0731",
      "provider": "deepseek",
      "providerName": "DeepSeek",
      "description": "DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....",
      "inputPer1M": 0.0443,
      "outputPer1M": 0.3,
      "blendedPer1M": 0.1082,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-07-31",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "liquid/lfm-3-1.7b",
      "slug": "liquid-lfm-3-1-7b",
      "name": "LiquidAI: LFM3-1.7B",
      "provider": "liquid",
      "providerName": "Liquid",
      "description": "A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used...",
      "inputPer1M": 0.08,
      "outputPer1M": 0.2,
      "blendedPer1M": 0.11,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 8192,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-11-06",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "deepseek/deepseek-v4-flash",
      "slug": "deepseek-deepseek-v4-flash",
      "name": "DeepSeek: DeepSeek V4 Flash 0423",
      "provider": "deepseek",
      "providerName": "DeepSeek",
      "description": "DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...",
      "inputPer1M": 0.09,
      "outputPer1M": 0.18,
      "blendedPer1M": 0.1125,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 393216,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-04-24",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.5-flash-02-23",
      "slug": "qwen-qwen3-5-flash-02-23",
      "name": "Qwen: Qwen3.5-Flash",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...",
      "inputPer1M": 0.065,
      "outputPer1M": 0.26,
      "blendedPer1M": 0.1138,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-02-25",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "nex-agi/nex-n2.5-pro",
      "slug": "nex-agi-nex-n2-5-pro",
      "name": "Nex AGI: Nex-N2.5-Pro",
      "provider": "nex-agi",
      "providerName": "Nex Agi",
      "description": "Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...",
      "inputPer1M": 0.075,
      "outputPer1M": 0.25,
      "blendedPer1M": 0.1188,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-09-08",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "meta-llama/llama-3.2-3b-instruct",
      "slug": "meta-llama-llama-3-2-3b-instruct",
      "name": "Meta: Llama 3.2 3B Instruct",
      "provider": "meta-llama",
      "providerName": "Meta Llama",
      "description": "Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...",
      "inputPer1M": 0.05,
      "outputPer1M": 0.33,
      "blendedPer1M": 0.12,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 117964,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2024-09-25",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3-coder-30b-a3b-instruct",
      "slug": "qwen-qwen3-coder-30b-a3b-instruct",
      "name": "Qwen: Qwen3 Coder 30B A3B Instruct",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...",
      "inputPer1M": 0.07,
      "outputPer1M": 0.28,
      "blendedPer1M": 0.1225,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-07-31",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "bytedance/ui-tars-1.5-7b",
      "slug": "bytedance-ui-tars-1-5-7b",
      "name": "ByteDance: UI-TARS 7B",
      "provider": "bytedance",
      "providerName": "Bytedance",
      "description": "UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...",
      "inputPer1M": 0.1,
      "outputPer1M": 0.2,
      "blendedPer1M": 0.125,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 2048,
      "inputModalities": [
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-07-22",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "meta/muse-spark-1.2-contributor",
      "slug": "meta-muse-spark-1-2-contributor",
      "name": "Meta: Muse Spark 1.2 Contributor",
      "provider": "meta",
      "providerName": "Meta",
      "description": "Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark...",
      "inputPer1M": 0.1,
      "outputPer1M": 0.2,
      "blendedPer1M": 0.125,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "text",
        "image",
        "video",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-08-21",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "meta/muse-spark-1.3-contributor",
      "slug": "meta-muse-spark-1-3-contributor",
      "name": "Meta: Muse Spark 1.3 Contributor",
      "provider": "meta",
      "providerName": "Meta",
      "description": "Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...",
      "inputPer1M": 0.1,
      "outputPer1M": 0.2,
      "blendedPer1M": 0.125,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "text",
        "image",
        "video",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-09-02",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "rekaai/reka-flash-3",
      "slug": "rekaai-reka-flash-3",
      "name": "Reka Flash 3",
      "provider": "rekaai",
      "providerName": "Rekaai",
      "description": "Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...",
      "inputPer1M": 0.1,
      "outputPer1M": 0.2,
      "blendedPer1M": 0.125,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 65536,
      "maxCompletionTokens": 58982,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-03-12",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "tencent/hy-mt2-30b-a3b",
      "slug": "tencent-hy-mt2-30b-a3b",
      "name": "Tencent: Hy-MT2-30B-A3B",
      "provider": "tencent",
      "providerName": "Tencent",
      "description": "Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...",
      "inputPer1M": 0.074,
      "outputPer1M": 0.295,
      "blendedPer1M": 0.1292,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 8192,
      "maxCompletionTokens": 4096,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-08-20",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "tencent/hy-mt2-7b",
      "slug": "tencent-hy-mt2-7b",
      "name": "Tencent: Hy-MT2-7B",
      "provider": "tencent",
      "providerName": "Tencent",
      "description": "Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.",
      "inputPer1M": 0.074,
      "outputPer1M": 0.295,
      "blendedPer1M": 0.1292,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 8192,
      "maxCompletionTokens": 4096,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-08-19",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3-32b",
      "slug": "qwen-qwen3-32b",
      "name": "Qwen: Qwen3 32B",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...",
      "inputPer1M": 0.08,
      "outputPer1M": 0.28,
      "blendedPer1M": 0.13,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-04-28",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "minimax/minimax-m3.1-flash",
      "slug": "minimax-minimax-m3-1-flash",
      "name": "MiniMax: MiniMax M3.1 Flash",
      "provider": "minimax",
      "providerName": "Minimax",
      "description": "MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...",
      "inputPer1M": 0.075,
      "outputPer1M": 0.3,
      "blendedPer1M": 0.1312,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 524288,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-10-19",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-oss-safeguard-20b",
      "slug": "openai-gpt-oss-safeguard-20b",
      "name": "OpenAI: gpt-oss-safeguard-20b",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...",
      "inputPer1M": 0.075,
      "outputPer1M": 0.3,
      "blendedPer1M": 0.1312,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-10-29",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "thinkingmachines/inkling-2-mini",
      "slug": "thinkingmachines-inkling-2-mini",
      "name": "Thinking Machines: Inkling 2 Mini",
      "provider": "thinkingmachines",
      "providerName": "Thinkingmachines",
      "description": "Inkling 2 Mini is an open-weight multimodal looped transformer from Thinking Machines Lab, with 3.4B active parameters out of 26.4B total (MoE). Its middle layers run three times with shared...",
      "inputPer1M": 0.075,
      "outputPer1M": 0.3,
      "blendedPer1M": 0.1312,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-11-21",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5-nano",
      "slug": "openai-gpt-5-nano",
      "name": "OpenAI: GPT-5 Nano",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...",
      "inputPer1M": 0.05,
      "outputPer1M": 0.4,
      "blendedPer1M": 0.1375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 400000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-08-07",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "tencent/hy3",
      "slug": "tencent-hy3",
      "name": "Tencent: Hy3",
      "provider": "tencent",
      "providerName": "Tencent",
      "description": "Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...",
      "inputPer1M": 0.0825,
      "outputPer1M": 0.33,
      "blendedPer1M": 0.1444,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-07-06",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "z-ai/glm-4.7-flash",
      "slug": "z-ai-glm-4-7-flash",
      "name": "Z.ai: GLM 4.7 Flash",
      "provider": "z-ai",
      "providerName": "Z Ai",
      "description": "As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...",
      "inputPer1M": 0.0605,
      "outputPer1M": 0.4,
      "blendedPer1M": 0.1454,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 200000,
      "maxCompletionTokens": 117964,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-01-19",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "meta-llama/llama-4-scout",
      "slug": "meta-llama-llama-4-scout",
      "name": "Meta: Llama 4 Scout",
      "provider": "meta-llama",
      "providerName": "Meta Llama",
      "description": "Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...",
      "inputPer1M": 0.1,
      "outputPer1M": 0.3,
      "blendedPer1M": 0.15,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1310720,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-04-05",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/ministral-8b-2512",
      "slug": "mistralai-ministral-8b-2512",
      "name": "Mistral: Ministral 3 8B 2512",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.",
      "inputPer1M": 0.15,
      "outputPer1M": 0.15,
      "blendedPer1M": 0.15,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 209715,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-12-02",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/voxtral-small-24b-2507",
      "slug": "mistralai-voxtral-small-24b-2507",
      "name": "Mistral: Voxtral Small 24B 2507",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...",
      "inputPer1M": 0.1,
      "outputPer1M": 0.3,
      "blendedPer1M": 0.15,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 32768,
      "maxCompletionTokens": 26214,
      "inputModalities": [
        "text",
        "audio",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": true,
      "tier": "ultra-budget",
      "createdAt": "2025-10-30",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3-14b",
      "slug": "qwen-qwen3-14b",
      "name": "Qwen: Qwen3 14B",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...",
      "inputPer1M": 0.12,
      "outputPer1M": 0.24,
      "blendedPer1M": 0.15,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 40960,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-04-28",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3-30b-a3b-instruct-2507",
      "slug": "qwen-qwen3-30b-a3b-instruct-2507",
      "name": "Qwen: Qwen3 30B A3B Instruct 2507",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...",
      "inputPer1M": 0.1,
      "outputPer1M": 0.3,
      "blendedPer1M": 0.15,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-07-29",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "ricursiveai/ripple-65b-preview",
      "slug": "ricursiveai-ripple-65b-preview",
      "name": "Ricursive: Ripple 65B Preview",
      "provider": "ricursiveai",
      "providerName": "Ricursiveai",
      "description": "Ripple-65B-Preview by ricursiveAI, a 65B model with native tool calling, served in BF16.",
      "inputPer1M": 0.1,
      "outputPer1M": 0.3,
      "blendedPer1M": 0.15,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-11-04",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "~deepseek/deepseek-flash-latest",
      "slug": "deepseek-deepseek-flash-latest",
      "name": "DeepSeek: DeepSeek Flash Latest",
      "provider": "deepseek",
      "providerName": "DeepSeek",
      "description": "This model always redirects to the latest model in the DeepSeek Flash family.",
      "inputPer1M": 0.036,
      "outputPer1M": 0.5,
      "blendedPer1M": 0.152,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-09-14",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "nvidia/nemotron-3-super-120b-a12b",
      "slug": "nvidia-nemotron-3-super-120b-a12b",
      "name": "NVIDIA: Nemotron 3 Super",
      "provider": "nvidia",
      "providerName": "NVIDIA",
      "description": "NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...",
      "inputPer1M": 0.075,
      "outputPer1M": 0.4,
      "blendedPer1M": 0.1563,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-03-11",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-oss-120b",
      "slug": "openai-gpt-oss-120b",
      "name": "OpenAI: gpt-oss-120b",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...",
      "inputPer1M": 0.09,
      "outputPer1M": 0.36,
      "blendedPer1M": 0.1575,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 117964,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-08-05",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemma-3-27b-it",
      "slug": "google-gemma-3-27b-it",
      "name": "Google: Gemma 3 27B",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...",
      "inputPer1M": 0.08,
      "outputPer1M": 0.45,
      "blendedPer1M": 0.1725,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 117964,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-03-12",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "bytedance-seed/seed-2.0-mini",
      "slug": "bytedance-seed-seed-2-0-mini",
      "name": "ByteDance Seed: Seed-2.0-Mini",
      "provider": "bytedance-seed",
      "providerName": "Bytedance Seed",
      "description": "Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort mode...",
      "inputPer1M": 0.1,
      "outputPer1M": 0.4,
      "blendedPer1M": 0.175,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-02-26",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-2.5-flash-lite",
      "slug": "google-gemini-2-5-flash-lite",
      "name": "Google: Gemini 2.5 Flash Lite",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...",
      "inputPer1M": 0.1,
      "outputPer1M": 0.4,
      "blendedPer1M": 0.175,
      "imagePer1K": 0.0001,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 65535,
      "inputModalities": [
        "text",
        "image",
        "file",
        "audio",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "ultra-budget",
      "createdAt": "2025-07-22",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-4.1-nano",
      "slug": "openai-gpt-4-1-nano",
      "name": "OpenAI: GPT-4.1 Nano",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...",
      "inputPer1M": 0.1,
      "outputPer1M": 0.4,
      "blendedPer1M": 0.175,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1047576,
      "maxCompletionTokens": 942818,
      "inputModalities": [
        "image",
        "text",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-04-14",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "xiaomi/mimo-v2.6-flash",
      "slug": "xiaomi-mimo-v2-6-flash",
      "name": "Xiaomi: MiMo-V2.6-Flash",
      "provider": "xiaomi",
      "providerName": "Xiaomi",
      "description": "MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...",
      "inputPer1M": 0.14,
      "outputPer1M": 0.28,
      "blendedPer1M": 0.175,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image",
        "video",
        "audio"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "ultra-budget",
      "createdAt": "2026-09-21",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "particle-ai/particle-1",
      "slug": "particle-ai-particle-1",
      "name": "Particle AI: Particle-1",
      "provider": "particle-ai",
      "providerName": "Particle Ai",
      "description": "Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data...",
      "inputPer1M": 0.07,
      "outputPer1M": 0.5,
      "blendedPer1M": 0.1775,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-10-28",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "meta-llama/llama-guard-4-12b",
      "slug": "meta-llama-llama-guard-4-12b",
      "name": "Meta: Llama Guard 4 12B",
      "provider": "meta-llama",
      "providerName": "Meta Llama",
      "description": "Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...",
      "inputPer1M": 0.18,
      "outputPer1M": 0.18,
      "blendedPer1M": 0.18,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 163840,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-04-30",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "prism-ml/ternary-bonsai-2-27b",
      "slug": "prism-ml-ternary-bonsai-2-27b",
      "name": "PrismML: Ternary Bonsai 2 27B",
      "provider": "prism-ml",
      "providerName": "Prism Ml",
      "description": "Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...",
      "inputPer1M": 0.075,
      "outputPer1M": 0.5,
      "blendedPer1M": 0.1813,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 32768,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-09-18",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "nex-agi/nex-n2.6",
      "slug": "nex-agi-nex-n2-6",
      "name": "Nex AGI: Nex-N2.6",
      "provider": "nex-agi",
      "providerName": "Nex Agi",
      "description": "Nex-N2.6 is an agentic model from Nex AGI, built on [GLM-5.3-Flash](https://huggingface.co/zai-org/GLM-5.3-Flash-BF16) with about 321B parameters. It is suited for computer use, coding, and long-horizon tasks that involve tools. Compared with...",
      "inputPer1M": 0.12,
      "outputPer1M": 0.4,
      "blendedPer1M": 0.19,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-11-10",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.5-9b",
      "slug": "qwen-qwen3-5-9b",
      "name": "Qwen: Qwen3.5-9B",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...",
      "inputPer1M": 0.17,
      "outputPer1M": 0.25,
      "blendedPer1M": 0.19,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-03-10",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "anthropic/claude-haiku-5.5",
      "slug": "anthropic-claude-haiku-5-5",
      "name": "Anthropic: Claude Haiku 5.5",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "description": "Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...",
      "inputPer1M": 0.1,
      "outputPer1M": 0.5,
      "blendedPer1M": 0.2,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-10-07",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "~anthropic/claude-haiku-latest",
      "slug": "anthropic-claude-haiku-latest",
      "name": "Anthropic: Claude Haiku Latest",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "description": "This model always redirects to the latest model in the Claude Haiku family.",
      "inputPer1M": 0.1,
      "outputPer1M": 0.5,
      "blendedPer1M": 0.2,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-04-27",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "meta/muse-ember",
      "slug": "meta-muse-ember",
      "name": "Meta: Muse Ember",
      "provider": "meta",
      "providerName": "Meta",
      "description": "Muse Ember is the smallest and most efficient model from Meta that’s designed for complex reasoning execution and the work agents repeat all day: tool calls, coding agent subtasks, routing,...",
      "inputPer1M": 0.1,
      "outputPer1M": 0.5,
      "blendedPer1M": 0.2,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "text",
        "image",
        "video",
        "file",
        "audio"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "ultra-budget",
      "createdAt": "2026-11-09",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/ministral-14b-2512",
      "slug": "mistralai-ministral-14b-2512",
      "name": "Mistral: Ministral 3 14B 2512",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...",
      "inputPer1M": 0.2,
      "outputPer1M": 0.2,
      "blendedPer1M": 0.2,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 209715,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-12-02",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "nvidia/nemotron-3.5-content-safety",
      "slug": "nvidia-nemotron-3-5-content-safety",
      "name": "NVIDIA: Nemotron 3.5 Content Safety",
      "provider": "nvidia",
      "providerName": "NVIDIA",
      "description": "NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...",
      "inputPer1M": 0.2,
      "outputPer1M": 0.2,
      "blendedPer1M": 0.2,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 117964,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-06-04",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "~openai/gpt-luna-latest",
      "slug": "openai-gpt-luna-latest",
      "name": "OpenAI: GPT Luna Latest",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "This model always redirects to the latest model in the GPT Luna family.",
      "inputPer1M": 0.1,
      "outputPer1M": 0.5,
      "blendedPer1M": 0.2,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-09-11",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-6-luna",
      "slug": "openai-gpt-6-luna",
      "name": "OpenAI: GPT-6 Luna",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...",
      "inputPer1M": 0.1,
      "outputPer1M": 0.5,
      "blendedPer1M": 0.2,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-09-22",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-6-luna-pro",
      "slug": "openai-gpt-6-luna-pro",
      "name": "OpenAI: GPT-6 Luna Pro",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
      "inputPer1M": 0.1,
      "outputPer1M": 0.5,
      "blendedPer1M": 0.2,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-09-22",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "liquid/lfm-2.5-24b-a2b",
      "slug": "liquid-lfm-2-5-24b-a2b",
      "name": "LiquidAI: LFM2.5-24B-A2B",
      "provider": "liquid",
      "providerName": "Liquid",
      "description": "LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...",
      "inputPer1M": 0.05,
      "outputPer1M": 0.7,
      "blendedPer1M": 0.2125,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 8192,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-10-13",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3-30b-a3b",
      "slug": "qwen-qwen3-30b-a3b",
      "name": "Qwen: Qwen3 30B A3B",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...",
      "inputPer1M": 0.12,
      "outputPer1M": 0.5,
      "blendedPer1M": 0.215,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 40960,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-04-28",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "nvidia/nemotron-3.5-super-vl",
      "slug": "nvidia-nemotron-3-5-super-vl",
      "name": "NVIDIA: Nemotron 3.5 Super VL",
      "provider": "nvidia",
      "providerName": "NVIDIA",
      "description": "NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...",
      "inputPer1M": 0.15,
      "outputPer1M": 0.47,
      "blendedPer1M": 0.23,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-10-15",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.8-flash",
      "slug": "qwen-qwen3-8-flash",
      "name": "Qwen: Qwen3.8 Flash",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.",
      "inputPer1M": 0.15,
      "outputPer1M": 0.47,
      "blendedPer1M": 0.23,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-08-26",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.8-omni-flash",
      "slug": "qwen-qwen3-8-omni-flash",
      "name": "Qwen: Qwen3.8 Omni Flash",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...",
      "inputPer1M": 0.15,
      "outputPer1M": 0.47,
      "blendedPer1M": 0.23,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image",
        "audio",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "ultra-budget",
      "createdAt": "2026-09-21",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemma-4-31b-it",
      "slug": "google-gemma-4-31b-it",
      "name": "Google: Gemma 4 31B",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...",
      "inputPer1M": 0.2,
      "outputPer1M": 0.4,
      "blendedPer1M": 0.25,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "image",
        "text",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-04-02",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "cohere/command-r-08-2024",
      "slug": "cohere-command-r-08-2024",
      "name": "Cohere: Command R (08-2024)",
      "provider": "cohere",
      "providerName": "Cohere",
      "description": "command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...",
      "inputPer1M": 0.15,
      "outputPer1M": 0.6,
      "blendedPer1M": 0.2625,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 4000,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2024-08-30",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "deepseek/deepseek-v4.1-flash-1017",
      "slug": "deepseek-deepseek-v4-1-flash-1017",
      "name": "DeepSeek: DeepSeek V4.1 Flash 1017",
      "provider": "deepseek",
      "providerName": "DeepSeek",
      "description": "DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...",
      "inputPer1M": 0.15,
      "outputPer1M": 0.6,
      "blendedPer1M": 0.2625,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 393216,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-10-17",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/mistral-small-2603",
      "slug": "mistralai-mistral-small-2603",
      "name": "Mistral: Mistral Small 4",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...",
      "inputPer1M": 0.15,
      "outputPer1M": 0.6,
      "blendedPer1M": 0.2625,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 209715,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-03-16",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-4o-mini",
      "slug": "openai-gpt-4o-mini",
      "name": "OpenAI: GPT-4o-mini",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...",
      "inputPer1M": 0.15,
      "outputPer1M": 0.6,
      "blendedPer1M": 0.2625,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2024-07-18",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-4o-mini-2024-07-18",
      "slug": "openai-gpt-4o-mini-2024-07-18",
      "name": "OpenAI: GPT-4o-mini (2024-07-18)",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...",
      "inputPer1M": 0.15,
      "outputPer1M": 0.6,
      "blendedPer1M": 0.2625,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2024-07-18",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3-vl-30b-a3b-instruct",
      "slug": "qwen-qwen3-vl-30b-a3b-instruct",
      "name": "Qwen: Qwen3 VL 30B A3B Instruct",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...",
      "inputPer1M": 0.15,
      "outputPer1M": 0.6,
      "blendedPer1M": 0.2625,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-10-06",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "upstage/solar-pro4",
      "slug": "upstage-solar-pro4",
      "name": "Upstage: Solar Pro 4",
      "provider": "upstage",
      "providerName": "Upstage",
      "description": "Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...",
      "inputPer1M": 0.15,
      "outputPer1M": 0.6,
      "blendedPer1M": 0.2625,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 524288,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-08-10",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "deepseek/deepseek-v3.2",
      "slug": "deepseek-deepseek-v3-2",
      "name": "DeepSeek: DeepSeek V3.2",
      "provider": "deepseek",
      "providerName": "DeepSeek",
      "description": "DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...",
      "inputPer1M": 0.26,
      "outputPer1M": 0.38,
      "blendedPer1M": 0.29,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 163840,
      "maxCompletionTokens": 147456,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-12-01",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3-coder-next",
      "slug": "qwen-qwen3-coder-next",
      "name": "Qwen: Qwen3 Coder Next",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...",
      "inputPer1M": 0.12,
      "outputPer1M": 0.8,
      "blendedPer1M": 0.29,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-02-04",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/mistral-saba",
      "slug": "mistralai-mistral-saba",
      "name": "Mistral: Saba",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...",
      "inputPer1M": 0.2,
      "outputPer1M": 0.6,
      "blendedPer1M": 0.3,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 32768,
      "maxCompletionTokens": 26214,
      "inputModalities": [
        "text",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2025-02-17",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.6-35b-a3b",
      "slug": "qwen-qwen3-6-35b-a3b",
      "name": "Qwen: Qwen3.6 35B A3B",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...",
      "inputPer1M": 0.1,
      "outputPer1M": 0.9,
      "blendedPer1M": 0.3,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "ultra-budget",
      "createdAt": "2026-04-27",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "deepseek/deepseek-v3.2-exp",
      "slug": "deepseek-deepseek-v3-2-exp",
      "name": "DeepSeek: DeepSeek V3.2 Exp",
      "provider": "deepseek",
      "providerName": "DeepSeek",
      "description": "DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...",
      "inputPer1M": 0.27,
      "outputPer1M": 0.41,
      "blendedPer1M": 0.305,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 163840,
      "maxCompletionTokens": 147456,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-09-29",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3-235b-a22b-2507",
      "slug": "qwen-qwen3-235b-a22b-2507",
      "name": "Qwen: Qwen3 235B A22B Instruct 2507",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instructio...",
      "inputPer1M": 0.14,
      "outputPer1M": 0.8,
      "blendedPer1M": 0.305,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 117964,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-07-21",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "z-ai/glm-4.5-air",
      "slug": "z-ai-glm-4-5-air",
      "name": "Z.ai: GLM 4.5 Air",
      "provider": "z-ai",
      "providerName": "Z Ai",
      "description": "GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...",
      "inputPer1M": 0.13,
      "outputPer1M": 0.85,
      "blendedPer1M": 0.31,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 98304,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-07-25",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "deepseek/deepseek-v4-flash-vision-exp",
      "slug": "deepseek-deepseek-v4-flash-vision-exp",
      "name": "DeepSeek: DeepSeek V4 Flash Vision Exp",
      "provider": "deepseek",
      "providerName": "DeepSeek",
      "description": "DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including...",
      "inputPer1M": 0.2156,
      "outputPer1M": 0.6468,
      "blendedPer1M": 0.3234,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 262144,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-08-21",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "kt/midm-k-3.0-pro",
      "slug": "kt-midm-k-3-0-pro",
      "name": "KT: Mi:dm K 3.0 Pro",
      "provider": "kt",
      "providerName": "Kt",
      "description": "Mi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters. It uses a hybrid architecture that mixes Mamba, MoE and attention layers.",
      "inputPer1M": 0.2,
      "outputPer1M": 0.8,
      "blendedPer1M": 0.35,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 261795,
      "maxCompletionTokens": 235615,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-11-05",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mancer/weaver",
      "slug": "mancer-weaver",
      "name": "Mancer: Weaver (alpha)",
      "provider": "mancer",
      "providerName": "Mancer",
      "description": "An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.",
      "inputPer1M": 0.3,
      "outputPer1M": 0.5,
      "blendedPer1M": 0.35,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 8000,
      "maxCompletionTokens": 6000,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2023-08-02",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3-next-80b-a3b-instruct",
      "slug": "qwen-qwen3-next-80b-a3b-instruct",
      "name": "Qwen: Qwen3 Next 80B A3B Instruct",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...",
      "inputPer1M": 0.1,
      "outputPer1M": 1.1,
      "blendedPer1M": 0.35,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-09-11",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "undi95/remm-slerp-l2-13b",
      "slug": "undi95-remm-slerp-l2-13b",
      "name": "ReMM SLERP 13B",
      "provider": "undi95",
      "providerName": "Undi95",
      "description": "A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge",
      "inputPer1M": 0.3,
      "outputPer1M": 0.5,
      "blendedPer1M": 0.35,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 6144,
      "maxCompletionTokens": 5529,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2023-07-22",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "thedrummer/cydonia-24b-v4.1",
      "slug": "thedrummer-cydonia-24b-v4-1",
      "name": "TheDrummer: Cydonia 24B V4.1",
      "provider": "thedrummer",
      "providerName": "Thedrummer",
      "description": "Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.",
      "inputPer1M": 0.3,
      "outputPer1M": 0.5,
      "blendedPer1M": 0.35,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 117964,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-09-27",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.5-35b-a3b",
      "slug": "qwen-qwen3-5-35b-a3b",
      "name": "Qwen: Qwen3.5-35B-A3B",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...",
      "inputPer1M": 0.14,
      "outputPer1M": 1,
      "blendedPer1M": 0.355,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 81920,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-02-25",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen-2.5-72b-instruct",
      "slug": "qwen-qwen-2-5-72b-instruct",
      "name": "Qwen2.5 72B Instruct",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...",
      "inputPer1M": 0.36,
      "outputPer1M": 0.4,
      "blendedPer1M": 0.37,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 32768,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2024-09-19",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3-vl-8b-instruct",
      "slug": "qwen-qwen3-vl-8b-instruct",
      "name": "Qwen: Qwen3 VL 8B Instruct",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...",
      "inputPer1M": 0.25,
      "outputPer1M": 0.75,
      "blendedPer1M": 0.375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-10-14",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "cognitivecomputations/dolphin-mistral-24b-venice-edition",
      "slug": "cognitivecomputations-dolphin-mistral-24b-venice-edition",
      "name": "Venice: Uncensored",
      "provider": "cognitivecomputations",
      "providerName": "Cognitivecomputations",
      "description": "Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...",
      "inputPer1M": 0.2,
      "outputPer1M": 0.9,
      "blendedPer1M": 0.375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 8192,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-07-09",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen-plus",
      "slug": "qwen-qwen-plus",
      "name": "Qwen: Qwen-Plus",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.",
      "inputPer1M": 0.26,
      "outputPer1M": 0.78,
      "blendedPer1M": 0.39,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 32768,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-02-01",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3-coder-flash",
      "slug": "qwen-qwen3-coder-flash",
      "name": "Qwen: Qwen3 Coder Flash",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...",
      "inputPer1M": 0.195,
      "outputPer1M": 0.975,
      "blendedPer1M": 0.39,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-09-17",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "thedrummer/unslopnemo-12b",
      "slug": "thedrummer-unslopnemo-12b",
      "name": "TheDrummer: UnslopNemo 12B",
      "provider": "thedrummer",
      "providerName": "Thedrummer",
      "description": "UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.",
      "inputPer1M": 0.4,
      "outputPer1M": 0.4,
      "blendedPer1M": 0.4,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1024000,
      "maxCompletionTokens": 819200,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2024-11-08",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/mistral-small-3.1-24b-instruct",
      "slug": "mistralai-mistral-small-3-1-24b-instruct",
      "name": "Mistral: Mistral Small 3.1 24B",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...",
      "inputPer1M": 0.351,
      "outputPer1M": 0.555,
      "blendedPer1M": 0.402,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 102400,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-03-17",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "z-ai/glm-5.3",
      "slug": "z-ai-glm-5-3",
      "name": "Z.ai: GLM 5.3",
      "provider": "z-ai",
      "providerName": "Z Ai",
      "description": "GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...",
      "inputPer1M": 0.0699,
      "outputPer1M": 1.4,
      "blendedPer1M": 0.4024,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-08-18",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "~z-ai/glm-latest",
      "slug": "z-ai-glm-latest",
      "name": "Z.ai: GLM Latest",
      "provider": "z-ai",
      "providerName": "Z Ai",
      "description": "This model always redirects to the latest GLM model from Z.ai.",
      "inputPer1M": 0.0699,
      "outputPer1M": 1.4,
      "blendedPer1M": 0.4024,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-08-19",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.6-flash",
      "slug": "qwen-qwen3-6-flash",
      "name": "Qwen: Qwen3.6 Flash",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...",
      "inputPer1M": 0.1875,
      "outputPer1M": 1.125,
      "blendedPer1M": 0.4219,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-04-27",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "deepseek/deepseek-chat-v3.1",
      "slug": "deepseek-deepseek-chat-v3-1",
      "name": "DeepSeek: DeepSeek V3.1",
      "provider": "deepseek",
      "providerName": "DeepSeek",
      "description": "DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...",
      "inputPer1M": 0.25,
      "outputPer1M": 0.95,
      "blendedPer1M": 0.425,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 163840,
      "maxCompletionTokens": 147456,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": true,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-08-21",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "deepseek/deepseek-chat-v3-0324",
      "slug": "deepseek-deepseek-chat-v3-0324",
      "name": "DeepSeek: DeepSeek V3 0324",
      "provider": "deepseek",
      "providerName": "DeepSeek",
      "description": "DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...",
      "inputPer1M": 0.25,
      "outputPer1M": 1,
      "blendedPer1M": 0.4375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 163840,
      "maxCompletionTokens": 147456,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-03-24",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "reflection/beam-1.0-501b-a23b",
      "slug": "reflection-beam-1-0-501b-a23b",
      "name": "Reflection: Beam 1.0 501B A23B",
      "provider": "reflection",
      "providerName": "Reflection",
      "description": "Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...",
      "inputPer1M": 0.25,
      "outputPer1M": 1,
      "blendedPer1M": 0.4375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-10-16",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "stepfun/step-3.7-flash",
      "slug": "stepfun-step-3-7-flash",
      "name": "StepFun: Step 3.7 Flash",
      "provider": "stepfun",
      "providerName": "Stepfun",
      "description": "Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...",
      "inputPer1M": 0.2,
      "outputPer1M": 1.15,
      "blendedPer1M": 0.4375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 230400,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-05-28",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "minimax/minimax-m2.5",
      "slug": "minimax-minimax-m2-5",
      "name": "MiniMax: MiniMax M2.5",
      "provider": "minimax",
      "providerName": "Minimax",
      "description": "MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...",
      "inputPer1M": 0.27,
      "outputPer1M": 0.95,
      "blendedPer1M": 0.44,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 198000,
      "maxCompletionTokens": 32768,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-02-12",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/codestral-2508",
      "slug": "mistralai-codestral-2508",
      "name": "Mistral: Codestral 2508",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)",
      "inputPer1M": 0.3,
      "outputPer1M": 0.9,
      "blendedPer1M": 0.45,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 256000,
      "maxCompletionTokens": 204800,
      "inputModalities": [
        "text",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-08-01",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.6-luna",
      "slug": "openai-gpt-5-6-luna",
      "name": "OpenAI: GPT-5.6 Luna",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...",
      "inputPer1M": 0.2,
      "outputPer1M": 1.2,
      "blendedPer1M": 0.45,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-07-09",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.6-luna-pro",
      "slug": "openai-gpt-5-6-luna-pro",
      "name": "OpenAI: GPT-5.6 Luna Pro",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
      "inputPer1M": 0.2,
      "outputPer1M": 1.2,
      "blendedPer1M": 0.45,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-07-09",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "z-ai/glm-4.6v",
      "slug": "z-ai-glm-4-6v",
      "name": "Z.ai: GLM 4.6V",
      "provider": "z-ai",
      "providerName": "Z Ai",
      "description": "GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...",
      "inputPer1M": 0.3,
      "outputPer1M": 0.9,
      "blendedPer1M": 0.45,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 32768,
      "inputModalities": [
        "image",
        "text",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-12-08",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "deepseek/deepseek-chat",
      "slug": "deepseek-deepseek-chat",
      "name": "DeepSeek: DeepSeek V3",
      "provider": "deepseek",
      "providerName": "DeepSeek",
      "description": "DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...",
      "inputPer1M": 0.2574,
      "outputPer1M": 1.0287,
      "blendedPer1M": 0.4502,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 163840,
      "maxCompletionTokens": 16000,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2024-12-26",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "deepseek/deepseek-v3.1-terminus",
      "slug": "deepseek-deepseek-v3-1-terminus",
      "name": "DeepSeek: DeepSeek V3.1 Terminus",
      "provider": "deepseek",
      "providerName": "DeepSeek",
      "description": "DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the mo...",
      "inputPer1M": 0.27,
      "outputPer1M": 1,
      "blendedPer1M": 0.4525,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 163840,
      "maxCompletionTokens": 147456,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-09-22",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.4-nano",
      "slug": "openai-gpt-5-4-nano",
      "name": "OpenAI: GPT-5.4 Nano",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...",
      "inputPer1M": 0.2,
      "outputPer1M": 1.25,
      "blendedPer1M": 0.4625,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 400000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-03-17",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3-coder",
      "slug": "qwen-qwen3-coder",
      "name": "Qwen: Qwen3 Coder 480B A35B",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...",
      "inputPer1M": 0.3,
      "outputPer1M": 1,
      "blendedPer1M": 0.475,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-07-23",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "thinkingmachines/inkling-2-small",
      "slug": "thinkingmachines-inkling-2-small",
      "name": "Thinking Machines: Inkling 2 Small",
      "provider": "thinkingmachines",
      "providerName": "Thinkingmachines",
      "description": "Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total. It is the first model in the second...",
      "inputPer1M": 0.3,
      "outputPer1M": 1,
      "blendedPer1M": 0.475,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-11-09",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "perceptron/perceptron-mk1",
      "slug": "perceptron-perceptron-mk1",
      "name": "Perceptron: Perceptron Mk1",
      "provider": "perceptron",
      "providerName": "Perceptron",
      "description": "Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...",
      "inputPer1M": 0.15,
      "outputPer1M": 1.5,
      "blendedPer1M": 0.4875,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 32768,
      "maxCompletionTokens": 8192,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-05-12",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "perceptron/perceptron-mk1.5",
      "slug": "perceptron-perceptron-mk1-5",
      "name": "Perceptron: Perceptron Mk1.5",
      "provider": "perceptron",
      "providerName": "Perceptron",
      "description": "Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...",
      "inputPer1M": 0.15,
      "outputPer1M": 1.5,
      "blendedPer1M": 0.4875,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 36864,
      "maxCompletionTokens": 8192,
      "inputModalities": [
        "text",
        "image",
        "video",
        "audio"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "budget",
      "createdAt": "2026-09-25",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "meta-llama/llama-4-maverick",
      "slug": "meta-llama-llama-4-maverick",
      "name": "Meta: Llama 4 Maverick",
      "provider": "meta-llama",
      "providerName": "Meta Llama",
      "description": "Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...",
      "inputPer1M": 0.35,
      "outputPer1M": 1,
      "blendedPer1M": 0.5125,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 524288,
      "maxCompletionTokens": 32768,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-04-05",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "minimax/minimax-m3",
      "slug": "minimax-minimax-m3",
      "name": "MiniMax: MiniMax M3",
      "provider": "minimax",
      "providerName": "Minimax",
      "description": "MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...",
      "inputPer1M": 0.3,
      "outputPer1M": 1.2,
      "blendedPer1M": 0.525,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 512000,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-05-31",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "motif-technologies/motif-3",
      "slug": "motif-technologies-motif-3",
      "name": "Motif Technologies: Motif 3",
      "provider": "motif-technologies",
      "providerName": "Motif Technologies",
      "description": "Motif 3 is a Mixture-of-Experts language model from Motif Technologies, with 314B total and 13.2B active parameters. It is a general-purpose multilingual model for English and Korean, particularly strong at...",
      "inputPer1M": 0.3,
      "outputPer1M": 1.2,
      "blendedPer1M": 0.525,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-11-02",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.8-27b",
      "slug": "qwen-qwen3-8-27b",
      "name": "Qwen: Qwen3.8 27B",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...",
      "inputPer1M": 0.06,
      "outputPer1M": 1.96,
      "blendedPer1M": 0.535,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1024000,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-08-14",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.5-27b",
      "slug": "qwen-qwen3-5-27b",
      "name": "Qwen: Qwen3.5-27B",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...",
      "inputPer1M": 0.195,
      "outputPer1M": 1.56,
      "blendedPer1M": 0.5363,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-02-25",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "xiaomi/mimo-v2.6-pro",
      "slug": "xiaomi-mimo-v2-6-pro",
      "name": "Xiaomi: MiMo-V2.6-Pro",
      "provider": "xiaomi",
      "providerName": "Xiaomi",
      "description": "MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...",
      "inputPer1M": 0.435,
      "outputPer1M": 0.87,
      "blendedPer1M": 0.5438,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image",
        "video",
        "audio"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "budget",
      "createdAt": "2026-09-21",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.7-plus",
      "slug": "qwen-qwen3-7-plus",
      "name": "Qwen: Qwen3.7 Plus",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...",
      "inputPer1M": 0.32,
      "outputPer1M": 1.28,
      "blendedPer1M": 0.56,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-06-03",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-3.1-flash-lite",
      "slug": "google-gemini-3-1-flash-lite",
      "name": "Google: Gemini 3.1 Flash Lite",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...",
      "inputPer1M": 0.25,
      "outputPer1M": 1.5,
      "blendedPer1M": 0.5625,
      "imagePer1K": 0.0003,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image",
        "video",
        "file",
        "audio"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "budget",
      "createdAt": "2026-05-07",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-3.1-flash-lite-preview",
      "slug": "google-gemini-3-1-flash-lite-preview",
      "name": "Google: Gemini 3.1 Flash Lite Preview",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...",
      "inputPer1M": 0.25,
      "outputPer1M": 1.5,
      "blendedPer1M": 0.5625,
      "imagePer1K": 0.0003,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image",
        "video",
        "file",
        "audio"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "budget",
      "createdAt": "2026-03-03",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-3.1-flash-lite-image",
      "slug": "google-gemini-3-1-flash-lite-image",
      "name": "Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)",
      "provider": "google",
      "providerName": "Google",
      "description": "Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...",
      "inputPer1M": 0.25,
      "outputPer1M": 1.5,
      "blendedPer1M": 0.5625,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 65536,
      "maxCompletionTokens": 58982,
      "inputModalities": [
        "image",
        "text"
      ],
      "outputModalities": [
        "image",
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-06-30",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "radixark/daisyrose-27b",
      "slug": "radixark-daisyrose-27b",
      "name": "RadixArk: DaisyRose 27B",
      "provider": "radixark",
      "providerName": "Radixark",
      "description": "DaisyRose 27B is an open-weight multimodal reasoning model from RadixArk, trained from [Qwen3.8 27B](https://openrouter.ai/qwen/qwen3.8-27b) using reinforcement learning only on long-horizon agent tasks, with no supervised fine-tuning or distillation. It is...",
      "inputPer1M": 0.15,
      "outputPer1M": 1.875,
      "blendedPer1M": 0.5813,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-11-21",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.5-plus-02-15",
      "slug": "qwen-qwen3-5-plus-02-15",
      "name": "Qwen: Qwen3.5 Plus 2026-02-15",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...",
      "inputPer1M": 0.26,
      "outputPer1M": 1.56,
      "blendedPer1M": 0.585,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-02-16",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "z-ai/glm-5.3-flashx",
      "slug": "z-ai-glm-5-3-flashx",
      "name": "Z.ai: GLM 5.3 FlashX",
      "provider": "z-ai",
      "providerName": "Z Ai",
      "description": "GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...",
      "inputPer1M": 0.37,
      "outputPer1M": 1.25,
      "blendedPer1M": 0.59,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-09-18",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "z-ai/glm-5.3-flashx-legal",
      "slug": "z-ai-glm-5-3-flashx-legal",
      "name": "Z.ai: GLM 5.3 FlashX Legal",
      "provider": "z-ai",
      "providerName": "Z Ai",
      "description": "GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. It adds legal-domain mid-training and post-training with reinforcement...",
      "inputPer1M": 0.37,
      "outputPer1M": 1.25,
      "blendedPer1M": 0.59,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-11-02",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "cohere/command-a-plus",
      "slug": "cohere-command-a-plus",
      "name": "Cohere: Command A+",
      "provider": "cohere",
      "providerName": "Cohere",
      "description": "Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...",
      "inputPer1M": 0.3,
      "outputPer1M": 1.5,
      "blendedPer1M": 0.6,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 192000,
      "maxCompletionTokens": 64000,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-09-22",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "thedrummer/skyfall-36b-v2",
      "slug": "thedrummer-skyfall-36b-v2",
      "name": "TheDrummer: Skyfall 36B V2",
      "provider": "thedrummer",
      "providerName": "Thedrummer",
      "description": "Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.",
      "inputPer1M": 0.55,
      "outputPer1M": 0.8,
      "blendedPer1M": 0.6125,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 32768,
      "maxCompletionTokens": 29491,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-03-10",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "tencent/hy4",
      "slug": "tencent-hy4",
      "name": "Tencent: Hy4",
      "provider": "tencent",
      "providerName": "Tencent",
      "description": "The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...",
      "inputPer1M": 0.417,
      "outputPer1M": 1.2505,
      "blendedPer1M": 0.6254,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-11-04",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3-vl-235b-a22b-instruct",
      "slug": "qwen-qwen3-vl-235b-a22b-instruct",
      "name": "Qwen: Qwen3 VL 235B A22B Instruct",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...",
      "inputPer1M": 0.21,
      "outputPer1M": 1.9,
      "blendedPer1M": 0.6325,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 32768,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-09-23",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "meta/muse-glimmer-30b",
      "slug": "meta-muse-glimmer-30b",
      "name": "Meta: Muse Glimmer 30B",
      "provider": "meta",
      "providerName": "Meta",
      "description": "Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...",
      "inputPer1M": 0.35,
      "outputPer1M": 1.5,
      "blendedPer1M": 0.6375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 117964,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-08-09",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "thinkingmachines/inkling-small",
      "slug": "thinkingmachines-inkling-small",
      "name": "Thinking Machines: Inkling Small",
      "provider": "thinkingmachines",
      "providerName": "Thinkingmachines",
      "description": "Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...",
      "inputPer1M": 0.45,
      "outputPer1M": 1.2,
      "blendedPer1M": 0.6375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 524288,
      "maxCompletionTokens": 262144,
      "inputModalities": [
        "text",
        "image",
        "audio"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "budget",
      "createdAt": "2026-07-30",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemma-2-27b-it",
      "slug": "google-gemma-2-27b-it",
      "name": "Google: Gemma 2 27B",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...",
      "inputPer1M": 0.65,
      "outputPer1M": 0.65,
      "blendedPer1M": 0.65,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 8192,
      "maxCompletionTokens": 2048,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2024-07-13",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.5-plus-20260420",
      "slug": "qwen-qwen3-5-plus-20260420",
      "name": "Qwen: Qwen3.5 Plus 2026-04-20",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...",
      "inputPer1M": 0.3,
      "outputPer1M": 1.8,
      "blendedPer1M": 0.675,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-04-27",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "bytedance-seed/seed-2.0-lite",
      "slug": "bytedance-seed-seed-2-0-lite",
      "name": "ByteDance Seed: Seed-2.0-Lite",
      "provider": "bytedance-seed",
      "providerName": "Bytedance Seed",
      "description": "Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...",
      "inputPer1M": 0.25,
      "outputPer1M": 2,
      "blendedPer1M": 0.6875,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-03-10",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5-mini",
      "slug": "openai-gpt-5-mini",
      "name": "OpenAI: GPT-5 Mini",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....",
      "inputPer1M": 0.25,
      "outputPer1M": 2,
      "blendedPer1M": 0.6875,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 400000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-08-07",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.1-codex-mini",
      "slug": "openai-gpt-5-1-codex-mini",
      "name": "OpenAI: GPT-5.1-Codex-Mini",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex",
      "inputPer1M": 0.25,
      "outputPer1M": 2,
      "blendedPer1M": 0.6875,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 400000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-11-13",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-4.1-mini",
      "slug": "openai-gpt-4-1-mini",
      "name": "OpenAI: GPT-4.1 Mini",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...",
      "inputPer1M": 0.4,
      "outputPer1M": 1.6,
      "blendedPer1M": 0.7,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1047576,
      "maxCompletionTokens": 32768,
      "inputModalities": [
        "image",
        "text",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-04-14",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "meta-llama/llama-3.3-70b-instruct",
      "slug": "meta-llama-llama-3-3-70b-instruct",
      "name": "Meta: Llama 3.3 70B Instruct",
      "provider": "meta-llama",
      "providerName": "Meta Llama",
      "description": "The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...",
      "inputPer1M": 0.71,
      "outputPer1M": 0.71,
      "blendedPer1M": 0.71,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 115200,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2024-12-06",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.5-122b-a10b",
      "slug": "qwen-qwen3-5-122b-a10b",
      "name": "Qwen: Qwen3.5-122B-A10B",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...",
      "inputPer1M": 0.26,
      "outputPer1M": 2.08,
      "blendedPer1M": 0.715,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-02-25",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "meta-llama/llama-3.1-70b-instruct",
      "slug": "meta-llama-llama-3-1-70b-instruct",
      "name": "Meta: Llama 3.1 70B Instruct",
      "provider": "meta-llama",
      "providerName": "Meta Llama",
      "description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...",
      "inputPer1M": 0.72,
      "outputPer1M": 0.72,
      "blendedPer1M": 0.72,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 8192,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2024-07-23",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.6-plus",
      "slug": "qwen-qwen3-6-plus",
      "name": "Qwen: Qwen3.6 Plus",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...",
      "inputPer1M": 0.325,
      "outputPer1M": 1.95,
      "blendedPer1M": 0.7313,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-04-02",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "z-ai/glm-4.7",
      "slug": "z-ai-glm-4-7",
      "name": "Z.ai: GLM 4.7",
      "provider": "z-ai",
      "providerName": "Z Ai",
      "description": "GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...",
      "inputPer1M": 0.4,
      "outputPer1M": 1.75,
      "blendedPer1M": 0.7375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 204800,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-12-22",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen-2.5-coder-32b-instruct",
      "slug": "qwen-qwen-2-5-coder-32b-instruct",
      "name": "Qwen2.5 Coder 32B Instruct",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...",
      "inputPer1M": 0.66,
      "outputPer1M": 1,
      "blendedPer1M": 0.745,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 32768,
      "maxCompletionTokens": 29491,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2024-11-11",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/mistral-large-2512",
      "slug": "mistralai-mistral-large-2512",
      "name": "Mistral: Mistral Large 3 2512",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.",
      "inputPer1M": 0.5,
      "outputPer1M": 1.5,
      "blendedPer1M": 0.75,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 209715,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-12-01",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/devstral-2512",
      "slug": "mistralai-devstral-2512",
      "name": "Mistral: Devstral 2 2512",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...",
      "inputPer1M": 0.4,
      "outputPer1M": 2,
      "blendedPer1M": 0.8,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 209715,
      "inputModalities": [
        "text",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-12-09",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "xiaomi/mimo-v2.5",
      "slug": "xiaomi-mimo-v2-5",
      "name": "Xiaomi: MiMo-V2.5",
      "provider": "xiaomi",
      "providerName": "Xiaomi",
      "description": "MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...",
      "inputPer1M": 0.4,
      "outputPer1M": 2,
      "blendedPer1M": 0.8,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "audio",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "budget",
      "createdAt": "2026-04-22",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "xiaomi/mimo-v2.5-pro",
      "slug": "xiaomi-mimo-v2-5-pro",
      "name": "Xiaomi: MiMo-V2.5-Pro",
      "provider": "xiaomi",
      "providerName": "Xiaomi",
      "description": "MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....",
      "inputPer1M": 0.48,
      "outputPer1M": 1.8,
      "blendedPer1M": 0.81,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-04-22",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "amazon/nova-2-lite-v1",
      "slug": "amazon-nova-2-lite-v1",
      "name": "Amazon: Nova 2 Lite",
      "provider": "amazon",
      "providerName": "Amazon",
      "description": "Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...",
      "inputPer1M": 0.3,
      "outputPer1M": 2.5,
      "blendedPer1M": 0.85,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 65535,
      "inputModalities": [
        "text",
        "image",
        "video",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-12-02",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-2.5-flash",
      "slug": "google-gemini-2-5-flash",
      "name": "Google: Gemini 2.5 Flash",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...",
      "inputPer1M": 0.3,
      "outputPer1M": 2.5,
      "blendedPer1M": 0.85,
      "imagePer1K": 0.0003,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 65535,
      "inputModalities": [
        "file",
        "image",
        "text",
        "audio",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "budget",
      "createdAt": "2025-06-17",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-3.5-flash-lite",
      "slug": "google-gemini-3-5-flash-lite",
      "name": "Google: Gemini 3.5 Flash Lite",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.",
      "inputPer1M": 0.3,
      "outputPer1M": 2.5,
      "blendedPer1M": 0.85,
      "imagePer1K": 0.0003,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image",
        "video",
        "file",
        "audio"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "budget",
      "createdAt": "2026-07-21",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-2.5-flash-image",
      "slug": "google-gemini-2-5-flash-image",
      "name": "Google: Nano Banana (Gemini 2.5 Flash Image)",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...",
      "inputPer1M": 0.3,
      "outputPer1M": 2.5,
      "blendedPer1M": 0.85,
      "imagePer1K": 0.0003,
      "requestCost": 0,
      "contextLength": 32768,
      "maxCompletionTokens": 8192,
      "inputModalities": [
        "image",
        "text"
      ],
      "outputModalities": [
        "image",
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-10-07",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "moondream/moondream3-preview",
      "slug": "moondream-moondream3-preview",
      "name": "Moondream: Moondream 3 Preview",
      "provider": "moondream",
      "providerName": "Moondream",
      "description": "Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...",
      "inputPer1M": 0.3,
      "outputPer1M": 2.5,
      "blendedPer1M": 0.85,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 32000,
      "maxCompletionTokens": 4096,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-10-15",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "moondream/moondream3.1-9b-a2b",
      "slug": "moondream-moondream3-1-9b-a2b",
      "name": "Moondream: Moondream 3.1",
      "provider": "moondream",
      "providerName": "Moondream",
      "description": "Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...",
      "inputPer1M": 0.3,
      "outputPer1M": 2.5,
      "blendedPer1M": 0.85,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 32000,
      "maxCompletionTokens": 4096,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-10-15",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen2.5-vl-72b-instruct",
      "slug": "qwen-qwen2-5-vl-72b-instruct",
      "name": "Qwen: Qwen2.5 VL 72B Instruct",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.",
      "inputPer1M": 0.8,
      "outputPer1M": 1,
      "blendedPer1M": 0.85,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 115200,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-02-01",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "sao10k/l3.1-euryale-70b",
      "slug": "sao10k-l3-1-euryale-70b",
      "name": "Sao10K: Llama 3.1 Euryale 70B v2.2",
      "provider": "sao10k",
      "providerName": "Sao10k",
      "description": "Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).",
      "inputPer1M": 0.85,
      "outputPer1M": 0.85,
      "blendedPer1M": 0.85,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2024-08-28",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "aion-labs/aion-3.5-mini",
      "slug": "aion-labs-aion-3-5-mini",
      "name": "AionLabs: Aion 3.5 Mini",
      "provider": "aion-labs",
      "providerName": "Aion Labs",
      "description": "Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...",
      "inputPer1M": 0.7,
      "outputPer1M": 1.4,
      "blendedPer1M": 0.875,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 32768,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-09-23",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "aion-labs/aion-3.0-mini",
      "slug": "aion-labs-aion-3-0-mini",
      "name": "AionLabs: Aion-3.0-Mini",
      "provider": "aion-labs",
      "providerName": "Aion Labs",
      "description": "Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...",
      "inputPer1M": 0.7,
      "outputPer1M": 1.4,
      "blendedPer1M": 0.875,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 32768,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-07-07",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "z-ai/glm-4.6",
      "slug": "z-ai-glm-4-6",
      "name": "Z.ai: GLM 4.6",
      "provider": "z-ai",
      "providerName": "Z Ai",
      "description": "Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...",
      "inputPer1M": 0.5,
      "outputPer1M": 2,
      "blendedPer1M": 0.875,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 204800,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-09-30",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/mistral-medium-3",
      "slug": "mistralai-mistral-medium-3",
      "name": "Mistral: Mistral Medium 3",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...",
      "inputPer1M": 0.44,
      "outputPer1M": 2.2,
      "blendedPer1M": 0.88,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 104857,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-05-07",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/mistral-medium-3.1",
      "slug": "mistralai-mistral-medium-3-1",
      "name": "Mistral: Mistral Medium 3.1",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...",
      "inputPer1M": 0.44,
      "outputPer1M": 2.2,
      "blendedPer1M": 0.88,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 104857,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-08-13",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "minimax/minimax-m2.7",
      "slug": "minimax-minimax-m2-7",
      "name": "MiniMax: MiniMax M2.7",
      "provider": "minimax",
      "providerName": "Minimax",
      "description": "MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...",
      "inputPer1M": 0.6,
      "outputPer1M": 1.8,
      "blendedPer1M": 0.9,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 196608,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-03-18",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "morph/morph-v3-fast",
      "slug": "morph-morph-v3-fast",
      "name": "Morph: Morph V3 Fast",
      "provider": "morph",
      "providerName": "Morph",
      "description": "Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_...",
      "inputPer1M": 0.8,
      "outputPer1M": 1.2,
      "blendedPer1M": 0.9,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-07-07",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "z-ai/glm-4.5v",
      "slug": "z-ai-glm-4-5v",
      "name": "Z.ai: GLM 4.5V",
      "provider": "z-ai",
      "providerName": "Z Ai",
      "description": "GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...",
      "inputPer1M": 0.6,
      "outputPer1M": 1.8,
      "blendedPer1M": 0.9,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 65536,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-08-11",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "nvidia/nemotron-3-ultra-550b-a55b",
      "slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "name": "NVIDIA: Nemotron 3 Ultra",
      "provider": "nvidia",
      "providerName": "NVIDIA",
      "description": "NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...",
      "inputPer1M": 0.5,
      "outputPer1M": 2.2,
      "blendedPer1M": 0.925,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-06-04",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "relace/relace-apply-3",
      "slug": "relace-relace-apply-3",
      "name": "Relace: Relace Apply 3",
      "provider": "relace",
      "providerName": "Relace",
      "description": "Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...",
      "inputPer1M": 0.85,
      "outputPer1M": 1.25,
      "blendedPer1M": 0.95,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 256000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-09-26",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "deepseek/deepseek-r1-0528",
      "slug": "deepseek-deepseek-r1-0528",
      "name": "DeepSeek: R1 0528",
      "provider": "deepseek",
      "providerName": "DeepSeek",
      "description": "May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...",
      "inputPer1M": 0.571,
      "outputPer1M": 2.286,
      "blendedPer1M": 0.9998,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 163840,
      "maxCompletionTokens": 32000,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": true,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-05-28",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "aion-labs/aion-2.0",
      "slug": "aion-labs-aion-2-0",
      "name": "AionLabs: Aion-2.0",
      "provider": "aion-labs",
      "providerName": "Aion Labs",
      "description": "Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....",
      "inputPer1M": 0.8,
      "outputPer1M": 1.6,
      "blendedPer1M": 1,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 32768,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-02-23",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "aion-labs/aion-rp-llama-3.1-8b",
      "slug": "aion-labs-aion-rp-llama-3-1-8b",
      "name": "AionLabs: Aion-RP 1.0 (8B)",
      "provider": "aion-labs",
      "providerName": "Aion Labs",
      "description": "Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...",
      "inputPer1M": 0.8,
      "outputPer1M": 1.6,
      "blendedPer1M": 1,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 32768,
      "maxCompletionTokens": 29491,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-02-04",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "bytedance-seed/seed-2-1-turbo",
      "slug": "bytedance-seed-seed-2-1-turbo",
      "name": "ByteDance Seed: Seed 2.1 Turbo",
      "provider": "bytedance-seed",
      "providerName": "Bytedance Seed",
      "description": "Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...",
      "inputPer1M": 0.5,
      "outputPer1M": 2.5,
      "blendedPer1M": 1,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-08-12",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "moonshotai/kimi-k2.5",
      "slug": "moonshotai-kimi-k2-5",
      "name": "MoonshotAI: Kimi K2.5",
      "provider": "moonshotai",
      "providerName": "Moonshotai",
      "description": "Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...",
      "inputPer1M": 0.5,
      "outputPer1M": 2.5,
      "blendedPer1M": 1,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-01-27",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "perplexity/sonar",
      "slug": "perplexity-sonar",
      "name": "Perplexity: Sonar",
      "provider": "perplexity",
      "providerName": "Perplexity",
      "description": "Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...",
      "inputPer1M": 1,
      "outputPer1M": 1,
      "blendedPer1M": 1,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 127072,
      "maxCompletionTokens": 114364,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-01-27",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "z-ai/glm-4.5",
      "slug": "z-ai-glm-4-5",
      "name": "Z.ai: GLM 4.5",
      "provider": "z-ai",
      "providerName": "Z Ai",
      "description": "GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...",
      "inputPer1M": 0.6,
      "outputPer1M": 2.2,
      "blendedPer1M": 1,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 98304,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-07-25",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "moonshotai/kimi-k2",
      "slug": "moonshotai-kimi-k2",
      "name": "MoonshotAI: Kimi K2 0711",
      "provider": "moonshotai",
      "providerName": "Moonshotai",
      "description": "Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...",
      "inputPer1M": 0.57,
      "outputPer1M": 2.3,
      "blendedPer1M": 1.0025,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 98304,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-07-11",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.6-27b",
      "slug": "qwen-qwen3-6-27b",
      "name": "Qwen: Qwen3.6 27B",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...",
      "inputPer1M": 0.32,
      "outputPer1M": 3.2,
      "blendedPer1M": 1.04,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 81920,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-04-27",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "deepseek/deepseek-v4-pro",
      "slug": "deepseek-deepseek-v4-pro",
      "name": "DeepSeek: DeepSeek V4 Pro 0423",
      "provider": "deepseek",
      "providerName": "DeepSeek",
      "description": "DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...",
      "inputPer1M": 0.9,
      "outputPer1M": 1.5,
      "blendedPer1M": 1.05,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 393216,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-04-24",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/mistral-large-4-0",
      "slug": "mistralai-mistral-large-4-0",
      "name": "Mistral: Mistral Large 4",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...",
      "inputPer1M": 0.7,
      "outputPer1M": 2.1,
      "blendedPer1M": 1.05,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 262144,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-10-06",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-audio-mini",
      "slug": "openai-gpt-audio-mini",
      "name": "OpenAI: GPT Audio Mini",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...",
      "inputPer1M": 0.6,
      "outputPer1M": 2.4,
      "blendedPer1M": 1.05,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text",
        "audio"
      ],
      "outputModalities": [
        "text",
        "audio"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": true,
      "tier": "budget",
      "createdAt": "2026-01-19",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "z-ai/glm-5.2",
      "slug": "z-ai-glm-5-2",
      "name": "Z.ai: GLM 5.2",
      "provider": "z-ai",
      "providerName": "Z Ai",
      "description": "GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...",
      "inputPer1M": 0.62,
      "outputPer1M": 2.42,
      "blendedPer1M": 1.07,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-06-16",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "moonshotai/kimi-k2-0905",
      "slug": "moonshotai-kimi-k2-0905",
      "name": "MoonshotAI: Kimi K2 0905",
      "provider": "moonshotai",
      "providerName": "Moonshotai",
      "description": "Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...",
      "inputPer1M": 0.6,
      "outputPer1M": 2.5,
      "blendedPer1M": 1.075,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 98304,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-09-04",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "moonshotai/kimi-k2-thinking",
      "slug": "moonshotai-kimi-k2-thinking",
      "name": "MoonshotAI: Kimi K2 Thinking",
      "provider": "moonshotai",
      "providerName": "Moonshotai",
      "description": "Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...",
      "inputPer1M": 0.6,
      "outputPer1M": 2.5,
      "blendedPer1M": 1.075,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 98304,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-11-06",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.5-397b-a17b",
      "slug": "qwen-qwen3-5-397b-a17b",
      "name": "Qwen: Qwen3.5 397B A17B",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...",
      "inputPer1M": 0.45,
      "outputPer1M": 3,
      "blendedPer1M": 1.0875,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 81920,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-02-16",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-3-flash-preview",
      "slug": "google-gemini-3-flash-preview",
      "name": "Google: Gemini 3 Flash Preview",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...",
      "inputPer1M": 0.5,
      "outputPer1M": 3,
      "blendedPer1M": 1.125,
      "imagePer1K": 0.0005,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image",
        "file",
        "audio",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "budget",
      "createdAt": "2025-12-17",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-3.1-flash-image-preview",
      "slug": "google-gemini-3-1-flash-image-preview",
      "name": "Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...",
      "inputPer1M": 0.5,
      "outputPer1M": 3,
      "blendedPer1M": 1.125,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 65536,
      "maxCompletionTokens": 58982,
      "inputModalities": [
        "image",
        "text"
      ],
      "outputModalities": [
        "image",
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-02-26",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-3.1-flash-image",
      "slug": "google-gemini-3-1-flash-image",
      "name": "Google: Nano Banana 2 (Gemini 3.1 Flash Image)",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...",
      "inputPer1M": 0.5,
      "outputPer1M": 3,
      "blendedPer1M": 1.125,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 32768,
      "inputModalities": [
        "image",
        "text"
      ],
      "outputModalities": [
        "image",
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-06-18",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "tencent/hy4-preview",
      "slug": "tencent-hy4-preview",
      "name": "Tencent: Hy4 preview",
      "provider": "tencent",
      "providerName": "Tencent",
      "description": "Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...",
      "inputPer1M": 0.7506,
      "outputPer1M": 2.2509,
      "blendedPer1M": 1.1257,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 64000,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-08-28",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "morph/morph-v3-large",
      "slug": "morph-morph-v3-large",
      "name": "Morph: Morph V3 Large",
      "provider": "morph",
      "providerName": "Morph",
      "description": "Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...",
      "inputPer1M": 0.9,
      "outputPer1M": 1.9,
      "blendedPer1M": 1.15,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2025-07-07",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "elorian/glimpse",
      "slug": "elorian-glimpse",
      "name": "Elorian: Glimpse",
      "provider": "elorian",
      "providerName": "Elorian",
      "description": "Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...",
      "inputPer1M": 0.6,
      "outputPer1M": 3,
      "blendedPer1M": 1.2,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 256000,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-10-17",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "moonshotai/kimi-k2.7-code",
      "slug": "moonshotai-kimi-k2-7-code",
      "name": "MoonshotAI: Kimi K2.7 Code",
      "provider": "moonshotai",
      "providerName": "Moonshotai",
      "description": "MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...",
      "inputPer1M": 0.6,
      "outputPer1M": 3,
      "blendedPer1M": 1.2,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "budget",
      "createdAt": "2026-06-12",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3-235b-a22b-thinking-2507",
      "slug": "qwen-qwen3-235b-a22b-thinking-2507",
      "name": "Qwen: Qwen3 235B A22B Thinking 2507",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...",
      "inputPer1M": 0.45,
      "outputPer1M": 3.5,
      "blendedPer1M": 1.2125,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": true,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2025-07-25",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-3.5-turbo-0613",
      "slug": "openai-gpt-3-5-turbo-0613",
      "name": "OpenAI: GPT-3.5 Turbo (older v0613)",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.",
      "inputPer1M": 1,
      "outputPer1M": 2,
      "blendedPer1M": 1.25,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 4095,
      "maxCompletionTokens": 3685,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2024-01-25",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "moonshotai/kimi-k2.6",
      "slug": "moonshotai-kimi-k2-6",
      "name": "MoonshotAI: Kimi K2.6",
      "provider": "moonshotai",
      "providerName": "Moonshotai",
      "description": "Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...",
      "inputPer1M": 0.65,
      "outputPer1M": 3.41,
      "blendedPer1M": 1.34,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 235929,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-04-20",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "amazon/nova-pro-v1",
      "slug": "amazon-nova-pro-v1",
      "name": "Amazon: Nova Pro 1.0",
      "provider": "amazon",
      "providerName": "Amazon",
      "description": "Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...",
      "inputPer1M": 0.8,
      "outputPer1M": 3.2,
      "blendedPer1M": 1.4,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 300000,
      "maxCompletionTokens": 5120,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2024-12-05",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "unbiased/pareto-26.10",
      "slug": "unbiased-pareto-26-10",
      "name": "Pareto 26.10",
      "provider": "unbiased",
      "providerName": "Unbiased",
      "description": "Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.",
      "inputPer1M": 0.8,
      "outputPer1M": 3.2,
      "blendedPer1M": 1.4,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-10-15",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "unbiased/pareto-26.10-preview",
      "slug": "unbiased-pareto-26-10-preview",
      "name": "Pareto 26.10 Preview",
      "provider": "unbiased",
      "providerName": "Unbiased",
      "description": "Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks. This is a preview of the...",
      "inputPer1M": 0.8,
      "outputPer1M": 3.2,
      "blendedPer1M": 1.4,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-10-01",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "~unbiased/pareto-latest",
      "slug": "unbiased-pareto-latest",
      "name": "Pareto Latest",
      "provider": "unbiased",
      "providerName": "Unbiased",
      "description": "This model always redirects to the latest model in the Pareto family.",
      "inputPer1M": 0.8,
      "outputPer1M": 3.2,
      "blendedPer1M": 1.4,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-10-13",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "stepfun/step-5-preview",
      "slug": "stepfun-step-5-preview",
      "name": "StepFun: Step 5 Preview",
      "provider": "stepfun",
      "providerName": "Stepfun",
      "description": "Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...",
      "inputPer1M": 1,
      "outputPer1M": 2.7,
      "blendedPer1M": 1.425,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 64000,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-10-08",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-3.6-flash",
      "slug": "google-gemini-3-6-flash",
      "name": "Google: Gemini 3.6 Flash",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...",
      "inputPer1M": 0.75,
      "outputPer1M": 3.75,
      "blendedPer1M": 1.5,
      "imagePer1K": 0.0008,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image",
        "video",
        "file",
        "audio"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "balanced",
      "createdAt": "2026-07-21",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-3.7-flash",
      "slug": "google-gemini-3-7-flash",
      "name": "Google: Gemini 3.7 Flash",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...",
      "inputPer1M": 0.75,
      "outputPer1M": 3.75,
      "blendedPer1M": 1.5,
      "imagePer1K": 0.0008,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image",
        "video",
        "file",
        "audio"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "balanced",
      "createdAt": "2026-08-13",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "nousresearch/hermes-4-405b",
      "slug": "nousresearch-hermes-4-405b",
      "name": "Nous: Hermes 4 405B",
      "provider": "nousresearch",
      "providerName": "Nous Research",
      "description": "Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...",
      "inputPer1M": 1,
      "outputPer1M": 3,
      "blendedPer1M": 1.5,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 117964,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": true,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2025-08-26",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "relace/relace-search",
      "slug": "relace-relace-search",
      "name": "Relace: Relace Search",
      "provider": "relace",
      "providerName": "Relace",
      "description": "The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...",
      "inputPer1M": 1,
      "outputPer1M": 3,
      "blendedPer1M": 1.5,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 256000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2025-12-08",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "z-ai/glm-5",
      "slug": "z-ai-glm-5",
      "name": "Z.ai: GLM 5",
      "provider": "z-ai",
      "providerName": "Z Ai",
      "description": "GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...",
      "inputPer1M": 1,
      "outputPer1M": 3.2,
      "blendedPer1M": 1.55,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 204800,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-02-11",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "x-ai/grok-4.20",
      "slug": "x-ai-grok-4-20",
      "name": "SpaceXSI: Grok 4.20",
      "provider": "x-ai",
      "providerName": "xAI",
      "description": "Grok 4.20 is a reasoning model from SpaceXSI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...",
      "inputPer1M": 1.25,
      "outputPer1M": 2.5,
      "blendedPer1M": 1.5625,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 2000000,
      "maxCompletionTokens": 1800000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-03-31",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "x-ai/grok-4.20-multi-agent",
      "slug": "x-ai-grok-4-20-multi-agent",
      "name": "SpaceXSI: Grok 4.20 Multi-Agent",
      "provider": "x-ai",
      "providerName": "xAI",
      "description": "Grok 4.20 Multi-Agent is a variant of SpaceXSI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...",
      "inputPer1M": 1.25,
      "outputPer1M": 2.5,
      "blendedPer1M": 1.5625,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 2000000,
      "maxCompletionTokens": 1800000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-03-31",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "x-ai/grok-4.3",
      "slug": "x-ai-grok-4-3",
      "name": "SpaceXSI: Grok 4.3",
      "provider": "x-ai",
      "providerName": "xAI",
      "description": "Grok 4.3 is a reasoning model from SpaceXSI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...",
      "inputPer1M": 1.25,
      "outputPer1M": 2.5,
      "blendedPer1M": 1.5625,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 900000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-04-30",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-3.8-flash",
      "slug": "google-gemini-3-8-flash",
      "name": "Google: Gemini 3.8 Flash",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.",
      "inputPer1M": 0.825,
      "outputPer1M": 4.125,
      "blendedPer1M": 1.65,
      "imagePer1K": 0.0008,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image",
        "video",
        "file",
        "audio"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "balanced",
      "createdAt": "2026-09-02",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "~openai/gpt-mini-latest",
      "slug": "openai-gpt-mini-latest",
      "name": "OpenAI: GPT Mini Latest",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "This model always redirects to the latest model in the GPT Mini family.",
      "inputPer1M": 0.75,
      "outputPer1M": 4.5,
      "blendedPer1M": 1.6875,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 400000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-04-27",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.4-mini",
      "slug": "openai-gpt-5-4-mini",
      "name": "OpenAI: GPT-5.4 Mini",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...",
      "inputPer1M": 0.75,
      "outputPer1M": 4.5,
      "blendedPer1M": 1.6875,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 400000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-03-17",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "sakana/sakana-namazu",
      "slug": "sakana-sakana-namazu",
      "name": "Sakana: Sakana Namazu",
      "provider": "sakana",
      "providerName": "Sakana",
      "description": "Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...",
      "inputPer1M": 0.95,
      "outputPer1M": 4,
      "blendedPer1M": 1.7125,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-08-11",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "thinkingmachines/inkling",
      "slug": "thinkingmachines-inkling",
      "name": "Thinking Machines: Inkling",
      "provider": "thinkingmachines",
      "providerName": "Thinkingmachines",
      "description": "Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...",
      "inputPer1M": 1,
      "outputPer1M": 4.05,
      "blendedPer1M": 1.7625,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 524288,
      "maxCompletionTokens": 471859,
      "inputModalities": [
        "text",
        "image",
        "audio"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "balanced",
      "createdAt": "2026-07-17",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "baidu/ernie-light-dt-1.0-intl",
      "slug": "baidu-ernie-light-dt-1-0-intl",
      "name": "Baidu: ERNIE-Light-DT-1.0",
      "provider": "baidu",
      "providerName": "Baidu",
      "description": "ERNIE-Light-DT-1.0 is based on open-source GLM models and includes research findings from Baidu Search's Lightning large model. It features Baidu Sparse Attention (BSA), a unique sparse attention mechanism developed by...",
      "inputPer1M": 1.13,
      "outputPer1M": 3.94,
      "blendedPer1M": 1.8325,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1024000,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-11-10",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "z-ai/glm-5-turbo",
      "slug": "z-ai-glm-5-turbo",
      "name": "Z.ai: GLM 5 Turbo",
      "provider": "z-ai",
      "providerName": "Z Ai",
      "description": "GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...",
      "inputPer1M": 1.2,
      "outputPer1M": 4,
      "blendedPer1M": 1.9,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 202752,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-03-15",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "z-ai/glm-5v-turbo",
      "slug": "z-ai-glm-5v-turbo",
      "name": "Z.ai: GLM 5V Turbo",
      "provider": "z-ai",
      "providerName": "Z Ai",
      "description": "GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...",
      "inputPer1M": 1.2,
      "outputPer1M": 4,
      "blendedPer1M": 1.9,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 202752,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "image",
        "text",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-04-01",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "writer/palmyra-x5",
      "slug": "writer-palmyra-x5",
      "name": "Writer: Palmyra X5",
      "provider": "writer",
      "providerName": "Writer",
      "description": "Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...",
      "inputPer1M": 0.6,
      "outputPer1M": 6,
      "blendedPer1M": 1.95,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1040000,
      "maxCompletionTokens": 8192,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-01-21",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "deepseek/deepseek-v4-pro-0813",
      "slug": "deepseek-deepseek-v4-pro-0813",
      "name": "DeepSeek: DeepSeek V4 Pro 0813",
      "provider": "deepseek",
      "providerName": "DeepSeek",
      "description": "DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.",
      "inputPer1M": 1.32,
      "outputPer1M": 3.96,
      "blendedPer1M": 1.98,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-08-12",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "anthropic/claude-haiku-4.5",
      "slug": "anthropic-claude-haiku-4-5",
      "name": "Anthropic: Claude Haiku 4.5",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "description": "Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...",
      "inputPer1M": 1,
      "outputPer1M": 5,
      "blendedPer1M": 2,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 200000,
      "maxCompletionTokens": 64000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2025-10-15",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "meta/muse-spark-1.1",
      "slug": "meta-muse-spark-1-1",
      "name": "Meta: Muse Spark 1.1",
      "provider": "meta",
      "providerName": "Meta",
      "description": "Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window....",
      "inputPer1M": 1.25,
      "outputPer1M": 4.25,
      "blendedPer1M": 2,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "text",
        "image",
        "video",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-07-16",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "meta/muse-spark-1.2",
      "slug": "meta-muse-spark-1-2",
      "name": "Meta: Muse Spark 1.2",
      "provider": "meta",
      "providerName": "Meta",
      "description": "Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window....",
      "inputPer1M": 1.25,
      "outputPer1M": 4.25,
      "blendedPer1M": 2,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "text",
        "image",
        "video",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-08-05",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "meta/muse-spark-1.3",
      "slug": "meta-muse-spark-1-3",
      "name": "Meta: Muse Spark 1.3",
      "provider": "meta",
      "providerName": "Meta",
      "description": "Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...",
      "inputPer1M": 1.25,
      "outputPer1M": 4.25,
      "blendedPer1M": 2,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "text",
        "image",
        "video",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-09-02",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "meta/muse-spark-open",
      "slug": "meta-muse-spark-open",
      "name": "Meta: Muse Spark Open",
      "provider": "meta",
      "providerName": "Meta",
      "description": "Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...",
      "inputPer1M": 1.25,
      "outputPer1M": 4.25,
      "blendedPer1M": 2,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "text",
        "image",
        "video",
        "file",
        "audio"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "balanced",
      "createdAt": "2026-10-15",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "~openai/gpt-terra-latest",
      "slug": "openai-gpt-terra-latest",
      "name": "OpenAI: GPT Terra Latest",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "This model always redirects to the latest model in the GPT Terra family.",
      "inputPer1M": 1,
      "outputPer1M": 5,
      "blendedPer1M": 2,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-09-11",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-6.1-terra",
      "slug": "openai-gpt-6-1-terra",
      "name": "OpenAI: GPT-6.1 Terra",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...",
      "inputPer1M": 1,
      "outputPer1M": 5,
      "blendedPer1M": 2,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-10-26",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-6.1-terra-pro",
      "slug": "openai-gpt-6-1-terra-pro",
      "name": "OpenAI: GPT-6.1 Terra Pro",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
      "inputPer1M": 1,
      "outputPer1M": 5,
      "blendedPer1M": 2,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-10-26",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "~deepseek/deepseek-pro-latest",
      "slug": "deepseek-deepseek-pro-latest",
      "name": "DeepSeek: DeepSeek Pro Latest",
      "provider": "deepseek",
      "providerName": "DeepSeek",
      "description": "This model always redirects to the latest model in the DeepSeek Pro family.",
      "inputPer1M": 0.0999,
      "outputPer1M": 8,
      "blendedPer1M": 2.0749,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 393216,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-09-14",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen4-max",
      "slug": "qwen-qwen4-max",
      "name": "Qwen: Qwen4 Max",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen4 Max is the flagship model in Alibaba's Qwen4 series. It accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default....",
      "inputPer1M": 1.425,
      "outputPer1M": 4.275,
      "blendedPer1M": 2.1375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-11-16",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "z-ai/glm-5.1",
      "slug": "z-ai-glm-5-1",
      "name": "Z.ai: GLM 5.1",
      "provider": "z-ai",
      "providerName": "Z Ai",
      "description": "GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...",
      "inputPer1M": 1.4,
      "outputPer1M": 4.4,
      "blendedPer1M": 2.15,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 204800,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-04-07",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.7-max",
      "slug": "qwen-qwen3-7-max",
      "name": "Qwen: Qwen3.7 Max",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...",
      "inputPer1M": 1.475,
      "outputPer1M": 4.425,
      "blendedPer1M": 2.2125,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-05-21",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5-image-mini",
      "slug": "openai-gpt-5-image-mini",
      "name": "OpenAI: GPT-5 Image Mini",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following...",
      "inputPer1M": 2.5,
      "outputPer1M": 2,
      "blendedPer1M": 2.375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 400000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "image",
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2025-10-16",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "moonshotai/kimi-k3.1-pro",
      "slug": "moonshotai-kimi-k3-1-pro",
      "name": "MoonshotAI: Kimi K3.1 Pro",
      "provider": "moonshotai",
      "providerName": "Moonshotai",
      "description": "Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...",
      "inputPer1M": 0.253,
      "outputPer1M": 8.8,
      "blendedPer1M": 2.3898,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-10-23",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "z-ai/glm-5.3-prime",
      "slug": "z-ai-glm-5-3-prime",
      "name": "Z.ai: GLM 5.3 Prime",
      "provider": "z-ai",
      "providerName": "Z Ai",
      "description": "GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...",
      "inputPer1M": 1.68,
      "outputPer1M": 5.28,
      "blendedPer1M": 2.58,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-09-23",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "~moonshotai/kimi-latest",
      "slug": "moonshotai-kimi-latest",
      "name": "MoonshotAI: Kimi Latest",
      "provider": "moonshotai",
      "providerName": "Moonshotai",
      "description": "This model always redirects to the latest model in the Kimi family.",
      "inputPer1M": 0.1824,
      "outputPer1M": 11.0055,
      "blendedPer1M": 2.8882,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-04-27",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-4-hydrogen",
      "slug": "google-gemini-4-hydrogen",
      "name": "Google: Gemini 4 Hydrogen",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than...",
      "inputPer1M": 1.5,
      "outputPer1M": 7.5,
      "blendedPer1M": 3,
      "imagePer1K": 0.0015,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "audio",
        "file",
        "image",
        "text",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "balanced",
      "createdAt": "2026-11-12",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "~google/gemini-flash-latest",
      "slug": "google-gemini-flash-latest",
      "name": "Google: Gemini Flash Latest",
      "provider": "google",
      "providerName": "Google",
      "description": "This model always redirects to the latest model in the Gemini Flash family.",
      "inputPer1M": 1.5,
      "outputPer1M": 7.5,
      "blendedPer1M": 3,
      "imagePer1K": 0.0015,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "audio",
        "file",
        "image",
        "text",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "balanced",
      "createdAt": "2026-04-27",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-nano-banana-2.1",
      "slug": "google-gemini-nano-banana-2-1",
      "name": "Google: Nano Banana 2.1",
      "provider": "google",
      "providerName": "Google",
      "description": "Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...",
      "inputPer1M": 1.5,
      "outputPer1M": 7.5,
      "blendedPer1M": 3,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 65536,
      "maxCompletionTokens": 58982,
      "inputModalities": [
        "image",
        "text"
      ],
      "outputModalities": [
        "image",
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-10-06",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/mistral-large",
      "slug": "mistralai-mistral-large",
      "name": "Mistral Large",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-24...",
      "inputPer1M": 2,
      "outputPer1M": 6,
      "blendedPer1M": 3,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 102400,
      "inputModalities": [
        "text",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2024-02-26",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/mistral-large-2407",
      "slug": "mistralai-mistral-large-2407",
      "name": "Mistral Large 2407",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407...",
      "inputPer1M": 2,
      "outputPer1M": 6,
      "blendedPer1M": 3,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 104857,
      "inputModalities": [
        "text",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2024-11-19",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/mistral-medium-3-5",
      "slug": "mistralai-mistral-medium-3-5",
      "name": "Mistral: Mistral Medium 3.5",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...",
      "inputPer1M": 1.5,
      "outputPer1M": 7.5,
      "blendedPer1M": 3,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 209715,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-04-30",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/mixtral-8x22b-instruct",
      "slug": "mistralai-mixtral-8x22b-instruct",
      "name": "Mistral: Mixtral 8x22B Instruct",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...",
      "inputPer1M": 2,
      "outputPer1M": 6,
      "blendedPer1M": 3,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 65536,
      "maxCompletionTokens": 52428,
      "inputModalities": [
        "text",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2024-04-17",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "mistralai/pixtral-large-2502",
      "slug": "mistralai-pixtral-large-2502",
      "name": "Mistral: Pixtral Large 2502",
      "provider": "mistralai",
      "providerName": "Mistral AI",
      "description": "Pixtral Large 2502 is the February 2025 version of Mistral AI's large multimodal model, following [Pixtral Large 2411](https://openrouter.ai/mistralai/pixtral-large-2411). It accepts text and image input, including documents, charts, and natural images,...",
      "inputPer1M": 2,
      "outputPer1M": 6,
      "blendedPer1M": 3,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 102400,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-11-20",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.8-2.4t-a95b",
      "slug": "qwen-qwen3-8-2-4t-a95b",
      "name": "Qwen: Qwen3.8 2.4T A95B",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...",
      "inputPer1M": 2,
      "outputPer1M": 6,
      "blendedPer1M": 3,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-08-12",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.8-max-0902",
      "slug": "qwen-qwen3-8-max-0902",
      "name": "Qwen: Qwen3.8 Max (0902)",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...",
      "inputPer1M": 2,
      "outputPer1M": 6,
      "blendedPer1M": 3,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-09-03",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "sakana/fugu-max",
      "slug": "sakana-fugu-max",
      "name": "Sakana: Fugu Max",
      "provider": "sakana",
      "providerName": "Sakana",
      "description": "Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...",
      "inputPer1M": 2,
      "outputPer1M": 6,
      "blendedPer1M": 3,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-09-11",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "x-ai/grok-4.5",
      "slug": "x-ai-grok-4-5",
      "name": "SpaceXSI: Grok 4.5",
      "provider": "x-ai",
      "providerName": "xAI",
      "description": "Grok 4.5 is a model from SpaceXSI with frontier performance on coding, knowledge work, and STEM.",
      "inputPer1M": 2,
      "outputPer1M": 6,
      "blendedPer1M": 3,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 500000,
      "maxCompletionTokens": 450000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-07-08",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "x-ai/grok-4.6",
      "slug": "x-ai-grok-4-6",
      "name": "SpaceXSI: Grok 4.6",
      "provider": "x-ai",
      "providerName": "xAI",
      "description": "Grok 4.6 is a model from SpaceXSI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).",
      "inputPer1M": 2,
      "outputPer1M": 6,
      "blendedPer1M": 3,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 500000,
      "maxCompletionTokens": 450000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-08-12",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "x-ai/grok-4.7",
      "slug": "x-ai-grok-4-7",
      "name": "SpaceXSI: Grok 4.7",
      "provider": "x-ai",
      "providerName": "xAI",
      "description": "Grok 4.7 is SpaceXSI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...",
      "inputPer1M": 2,
      "outputPer1M": 6,
      "blendedPer1M": 3,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 500000,
      "maxCompletionTokens": 450000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-09-21",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "~x-ai/grok-latest",
      "slug": "x-ai-grok-latest",
      "name": "xAI: Grok Latest",
      "provider": "x-ai",
      "providerName": "xAI",
      "description": "This model always redirects to the latest Grok model from xAI.",
      "inputPer1M": 2,
      "outputPer1M": 6,
      "blendedPer1M": 3,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 500000,
      "maxCompletionTokens": 450000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-07-08",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "anthracite-org/magnum-v4-72b",
      "slug": "anthracite-org-magnum-v4-72b",
      "name": "Magnum v4 72B",
      "provider": "anthracite-org",
      "providerName": "Anthracite Org",
      "description": "This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus). The model is fine-tuned on top of [Qwe...",
      "inputPer1M": 2.5,
      "outputPer1M": 5,
      "blendedPer1M": 3.125,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 32768,
      "maxCompletionTokens": 4096,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2024-10-22",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-3.5-turbo-16k",
      "slug": "openai-gpt-3-5-turbo-16k",
      "name": "OpenAI: GPT-3.5 Turbo 16k",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...",
      "inputPer1M": 3,
      "outputPer1M": 4,
      "blendedPer1M": 3.25,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 16385,
      "maxCompletionTokens": 4096,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2023-08-28",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-3.5-flash",
      "slug": "google-gemini-3-5-flash",
      "name": "Google: Gemini 3.5 Flash",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...",
      "inputPer1M": 1.5,
      "outputPer1M": 9,
      "blendedPer1M": 3.375,
      "imagePer1K": 0.0015,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image",
        "video",
        "file",
        "audio"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "balanced",
      "createdAt": "2026-05-19",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-omni-1.1-flash",
      "slug": "google-gemini-omni-1-1-flash",
      "name": "Google: Gemini Omni 1.1 Flash",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini Omni 1.1 Flash is Google's native multimodal video generation and editing model, the generally available successor to Gemini Omni Flash Preview. It is suited for text-to-video, image-to-video, first and...",
      "inputPer1M": 1.5,
      "outputPer1M": 9,
      "blendedPer1M": 3.375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text",
        "video"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-11-04",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-omni-1.2-flash",
      "slug": "google-gemini-omni-1-2-flash",
      "name": "Google: Gemini Omni 1.2 Flash",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash. It generates clips up to 15 seconds long with native...",
      "inputPer1M": 1.5,
      "outputPer1M": 9,
      "blendedPer1M": 3.375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text",
        "video"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-11-05",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-2.5-pro",
      "slug": "google-gemini-2-5-pro",
      "name": "Google: Gemini 2.5 Pro",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...",
      "inputPer1M": 1.25,
      "outputPer1M": 10,
      "blendedPer1M": 3.4375,
      "imagePer1K": 0.0013,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "image",
        "file",
        "audio",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "balanced",
      "createdAt": "2025-06-17",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-2.5-pro-preview",
      "slug": "google-gemini-2-5-pro-preview",
      "name": "Google: Gemini 2.5 Pro Preview 06-05",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...",
      "inputPer1M": 1.25,
      "outputPer1M": 10,
      "blendedPer1M": 3.4375,
      "imagePer1K": 0.0013,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "file",
        "image",
        "text",
        "audio"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "balanced",
      "createdAt": "2025-06-05",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5",
      "slug": "openai-gpt-5",
      "name": "OpenAI: GPT-5",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...",
      "inputPer1M": 1.25,
      "outputPer1M": 10,
      "blendedPer1M": 3.4375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 400000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2025-08-07",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.1",
      "slug": "openai-gpt-5-1",
      "name": "OpenAI: GPT-5.1",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...",
      "inputPer1M": 1.25,
      "outputPer1M": 10,
      "blendedPer1M": 3.4375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 400000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "image",
        "text",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2025-11-13",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.1-codex",
      "slug": "openai-gpt-5-1-codex",
      "name": "OpenAI: GPT-5.1-Codex",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....",
      "inputPer1M": 1.25,
      "outputPer1M": 10,
      "blendedPer1M": 3.4375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 400000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2025-11-13",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.1-codex-max",
      "slug": "openai-gpt-5-1-codex-max",
      "name": "OpenAI: GPT-5.1-Codex-Max",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...",
      "inputPer1M": 1.25,
      "outputPer1M": 10,
      "blendedPer1M": 3.4375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 400000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2025-12-04",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-4.1",
      "slug": "openai-gpt-4-1",
      "name": "OpenAI: GPT-4.1",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...",
      "inputPer1M": 2,
      "outputPer1M": 8,
      "blendedPer1M": 3.5,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1047576,
      "maxCompletionTokens": 32768,
      "inputModalities": [
        "image",
        "text",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2025-04-14",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/o3",
      "slug": "openai-o3",
      "name": "OpenAI: o3",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....",
      "inputPer1M": 2,
      "outputPer1M": 8,
      "blendedPer1M": 3.5,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 200000,
      "maxCompletionTokens": 100000,
      "inputModalities": [
        "image",
        "text",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2025-04-16",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "perplexity/sonar-deep-research",
      "slug": "perplexity-sonar-deep-research",
      "name": "Perplexity: Sonar Deep Research",
      "provider": "perplexity",
      "providerName": "Perplexity",
      "description": "Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...",
      "inputPer1M": 2,
      "outputPer1M": 8,
      "blendedPer1M": 3.5,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 115200,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2025-03-07",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "perplexity/sonar-reasoning-pro",
      "slug": "perplexity-sonar-reasoning-pro",
      "name": "Perplexity: Sonar Reasoning Pro",
      "provider": "perplexity",
      "providerName": "Perplexity",
      "description": "Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R...",
      "inputPer1M": 2,
      "outputPer1M": 8,
      "blendedPer1M": 3.5,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 115200,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2025-03-07",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "aion-labs/aion-3.5",
      "slug": "aion-labs-aion-3-5",
      "name": "AionLabs: Aion 3.5",
      "provider": "aion-labs",
      "providerName": "Aion Labs",
      "description": "Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...",
      "inputPer1M": 3,
      "outputPer1M": 6,
      "blendedPer1M": 3.75,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 32768,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-09-23",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "aion-labs/aion-3.0",
      "slug": "aion-labs-aion-3-0",
      "name": "AionLabs: Aion-3.0",
      "provider": "aion-labs",
      "providerName": "Aion Labs",
      "description": "Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...",
      "inputPer1M": 3,
      "outputPer1M": 6,
      "blendedPer1M": 3.75,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 32768,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-07-07",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "unbiased/pareto-26.9",
      "slug": "unbiased-pareto-26-9",
      "name": "Pareto 26.9",
      "provider": "unbiased",
      "providerName": "Unbiased",
      "description": "Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.",
      "inputPer1M": 2.5,
      "outputPer1M": 7.5,
      "blendedPer1M": 3.75,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 262144,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-10-13",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "anthropic/claude-sonnet-5",
      "slug": "anthropic-claude-sonnet-5",
      "name": "Anthropic: Claude Sonnet 5",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "description": "Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...",
      "inputPer1M": 2,
      "outputPer1M": 10,
      "blendedPer1M": 4,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-06-30",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "anthropic/claude-sonnet-5.5",
      "slug": "anthropic-claude-sonnet-5-5",
      "name": "Anthropic: Claude Sonnet 5.5",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "description": "Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...",
      "inputPer1M": 2,
      "outputPer1M": 10,
      "blendedPer1M": 4,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-09-28",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "~anthropic/claude-sonnet-latest",
      "slug": "anthropic-claude-sonnet-latest",
      "name": "Anthropic: Claude Sonnet Latest",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "description": "This model always redirects to the latest model in the Claude Sonnet family.",
      "inputPer1M": 2,
      "outputPer1M": 10,
      "blendedPer1M": 4,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-04-27",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-4-argon",
      "slug": "google-gemini-4-argon",
      "name": "Google: Gemini 4 Argon",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...",
      "inputPer1M": 2,
      "outputPer1M": 10,
      "blendedPer1M": 4,
      "imagePer1K": 0.002,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "audio",
        "file",
        "image",
        "text",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "balanced",
      "createdAt": "2026-10-13",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-4-carbon",
      "slug": "google-gemini-4-carbon",
      "name": "Google: Gemini 4 Carbon",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode...",
      "inputPer1M": 2,
      "outputPer1M": 10,
      "blendedPer1M": 4,
      "imagePer1K": 0.002,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "audio",
        "file",
        "image",
        "text",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "balanced",
      "createdAt": "2026-11-10",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "~google/gemini-pro-latest",
      "slug": "google-gemini-pro-latest",
      "name": "Google: Gemini Pro Latest",
      "provider": "google",
      "providerName": "Google",
      "description": "This model always redirects to the latest model in the Gemini Pro family.",
      "inputPer1M": 2,
      "outputPer1M": 10,
      "blendedPer1M": 4,
      "imagePer1K": 0.002,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "audio",
        "file",
        "image",
        "text",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "balanced",
      "createdAt": "2026-04-27",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "~openai/gpt-sol-latest",
      "slug": "openai-gpt-sol-latest",
      "name": "OpenAI: GPT Sol Latest",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "This model always redirects to the latest model in the GPT Sol family.",
      "inputPer1M": 2,
      "outputPer1M": 10,
      "blendedPer1M": 4,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-09-11",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-6-sol",
      "slug": "openai-gpt-6-sol",
      "name": "OpenAI: GPT-6 Sol",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...",
      "inputPer1M": 2,
      "outputPer1M": 10,
      "blendedPer1M": 4,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-09-22",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-6-sol-pro",
      "slug": "openai-gpt-6-sol-pro",
      "name": "OpenAI: GPT-6 Sol Pro",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
      "inputPer1M": 2,
      "outputPer1M": 10,
      "blendedPer1M": 4,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-09-22",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-6.1-sol",
      "slug": "openai-gpt-6-1-sol",
      "name": "OpenAI: GPT-6.1 Sol",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...",
      "inputPer1M": 2,
      "outputPer1M": 10,
      "blendedPer1M": 4,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-09-29",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-6.1-sol-pro",
      "slug": "openai-gpt-6-1-sol-pro",
      "name": "OpenAI: GPT-6.1 Sol Pro",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
      "inputPer1M": 2,
      "outputPer1M": 10,
      "blendedPer1M": 4,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-09-29",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-6.2-sol",
      "slug": "openai-gpt-6-2-sol",
      "name": "OpenAI: GPT-6.2 Sol",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-6.2 Sol is an upgrade to GPT-6.1 Sol from OpenAI, positioned below the flagship GPT-6.2 Astra in the GPT-6.2 series. It is an efficient, versatile model for everyday work, suited...",
      "inputPer1M": 2,
      "outputPer1M": 10,
      "blendedPer1M": 4,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-11-17",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-6.2-sol-pro",
      "slug": "openai-gpt-6-2-sol-pro",
      "name": "OpenAI: GPT-6.2 Sol Pro",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-6.2 Sol Pro is the same underlying model as [GPT-6.2 Sol](https://openrouter.ai/openai/gpt-6.2-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
      "inputPer1M": 2,
      "outputPer1M": 10,
      "blendedPer1M": 4,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-11-17",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "moonshotai/kimi-k3",
      "slug": "moonshotai-kimi-k3",
      "name": "MoonshotAI: Kimi K3",
      "provider": "moonshotai",
      "providerName": "Moonshotai",
      "description": "Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...",
      "inputPer1M": 0.192,
      "outputPer1M": 16,
      "blendedPer1M": 4.144,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-07-16",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "cohere/command-a",
      "slug": "cohere-command-a",
      "name": "Cohere: Command A",
      "provider": "cohere",
      "providerName": "Cohere",
      "description": "Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...",
      "inputPer1M": 2.5,
      "outputPer1M": 10,
      "blendedPer1M": 4.375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 256000,
      "maxCompletionTokens": 8192,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2025-03-13",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "cohere/command-r-plus-08-2024",
      "slug": "cohere-command-r-plus-08-2024",
      "name": "Cohere: Command R+ (08-2024)",
      "provider": "cohere",
      "providerName": "Cohere",
      "description": "command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...",
      "inputPer1M": 2.5,
      "outputPer1M": 10,
      "blendedPer1M": 4.375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 4000,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2024-08-30",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-audio",
      "slug": "openai-gpt-audio",
      "name": "OpenAI: GPT Audio",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...",
      "inputPer1M": 2.5,
      "outputPer1M": 10,
      "blendedPer1M": 4.375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text",
        "audio"
      ],
      "outputModalities": [
        "text",
        "audio"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": true,
      "tier": "balanced",
      "createdAt": "2026-01-19",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-4o",
      "slug": "openai-gpt-4o",
      "name": "OpenAI: GPT-4o",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...",
      "inputPer1M": 2.5,
      "outputPer1M": 10,
      "blendedPer1M": 4.375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2024-05-13",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-4o-2024-08-06",
      "slug": "openai-gpt-4o-2024-08-06",
      "name": "OpenAI: GPT-4o (2024-08-06)",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o (\"o\" for \"omni\"...",
      "inputPer1M": 2.5,
      "outputPer1M": 10,
      "blendedPer1M": 4.375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2024-08-06",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-4o-2024-11-20",
      "slug": "openai-gpt-4o-2024-11-20",
      "name": "OpenAI: GPT-4o (2024-11-20)",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...",
      "inputPer1M": 2.5,
      "outputPer1M": 10,
      "blendedPer1M": 4.375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 16384,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2024-11-20",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-3.1-pro-preview",
      "slug": "google-gemini-3-1-pro-preview",
      "name": "Google: Gemini 3.1 Pro Preview",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...",
      "inputPer1M": 2,
      "outputPer1M": 12,
      "blendedPer1M": 4.5,
      "imagePer1K": 0.002,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "audio",
        "file",
        "image",
        "text",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "balanced",
      "createdAt": "2026-02-19",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-3.1-pro-preview-customtools",
      "slug": "google-gemini-3-1-pro-preview-customtools",
      "name": "Google: Gemini 3.1 Pro Preview Custom Tools",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...",
      "inputPer1M": 2,
      "outputPer1M": 12,
      "blendedPer1M": 4.5,
      "imagePer1K": 0.002,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 65536,
      "inputModalities": [
        "text",
        "audio",
        "image",
        "video",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "balanced",
      "createdAt": "2026-02-25",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-3-pro-image-preview",
      "slug": "google-gemini-3-pro-image-preview",
      "name": "Google: Nano Banana Pro (Gemini 3 Pro Image Preview)",
      "provider": "google",
      "providerName": "Google",
      "description": "Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...",
      "inputPer1M": 2,
      "outputPer1M": 12,
      "blendedPer1M": 4.5,
      "imagePer1K": 0.002,
      "requestCost": 0,
      "contextLength": 65536,
      "maxCompletionTokens": 32768,
      "inputModalities": [
        "image",
        "text"
      ],
      "outputModalities": [
        "image",
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2025-11-20",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-3-pro-image",
      "slug": "google-gemini-3-pro-image",
      "name": "Google: Nano Banana Pro (Gemini 3 Pro Image)",
      "provider": "google",
      "providerName": "Google",
      "description": "Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...",
      "inputPer1M": 2,
      "outputPer1M": 12,
      "blendedPer1M": 4.5,
      "imagePer1K": 0.002,
      "requestCost": 0,
      "contextLength": 131072,
      "maxCompletionTokens": 32768,
      "inputModalities": [
        "image",
        "text"
      ],
      "outputModalities": [
        "image",
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-06-18",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.6-terra",
      "slug": "openai-gpt-5-6-terra",
      "name": "OpenAI: GPT-5.6 Terra",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...",
      "inputPer1M": 2,
      "outputPer1M": 12,
      "blendedPer1M": 4.5,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-07-09",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.6-terra-pro",
      "slug": "openai-gpt-5-6-terra-pro",
      "name": "OpenAI: GPT-5.6 Terra Pro",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
      "inputPer1M": 2,
      "outputPer1M": 12,
      "blendedPer1M": 4.5,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "balanced",
      "createdAt": "2026-07-09",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.2",
      "slug": "openai-gpt-5-2",
      "name": "OpenAI: GPT-5.2",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...",
      "inputPer1M": 1.75,
      "outputPer1M": 14,
      "blendedPer1M": 4.8125,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 400000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2025-12-10",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.2-chat",
      "slug": "openai-gpt-5-2-chat",
      "name": "OpenAI: GPT-5.2 Chat",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...",
      "inputPer1M": 1.75,
      "outputPer1M": 14,
      "blendedPer1M": 4.8125,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 32000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2025-12-10",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.2-codex",
      "slug": "openai-gpt-5-2-codex",
      "name": "OpenAI: GPT-5.2-Codex",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....",
      "inputPer1M": 1.75,
      "outputPer1M": 14,
      "blendedPer1M": 4.8125,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 400000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-01-14",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.3-codex",
      "slug": "openai-gpt-5-3-codex",
      "name": "OpenAI: GPT-5.3-Codex",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...",
      "inputPer1M": 1.75,
      "outputPer1M": 14,
      "blendedPer1M": 4.8125,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 400000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-02-24",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "amazon/nova-premier-v1",
      "slug": "amazon-nova-premier-v1",
      "name": "Amazon: Nova Premier 1.0",
      "provider": "amazon",
      "providerName": "Amazon",
      "description": "Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.",
      "inputPer1M": 2.5,
      "outputPer1M": 12.5,
      "blendedPer1M": 5,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 32000,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2025-10-31",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "xiaomi/mimo-v2.6-pro-ultraspeed",
      "slug": "xiaomi-mimo-v2-6-pro-ultraspeed",
      "name": "Xiaomi: MiMo-V2.6-Pro-UltraSpeed",
      "provider": "xiaomi",
      "providerName": "Xiaomi",
      "description": "MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x...",
      "inputPer1M": 4.35,
      "outputPer1M": 8.7,
      "blendedPer1M": 5.4375,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image",
        "video",
        "audio"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "flagship",
      "createdAt": "2026-09-21",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.4",
      "slug": "openai-gpt-5-4",
      "name": "OpenAI: GPT-5.4",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...",
      "inputPer1M": 2.5,
      "outputPer1M": 15,
      "blendedPer1M": 5.625,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-03-05",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "anthropic/claude-sonnet-4.5",
      "slug": "anthropic-claude-sonnet-4-5",
      "name": "Anthropic: Claude Sonnet 4.5",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "description": "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...",
      "inputPer1M": 3,
      "outputPer1M": 15,
      "blendedPer1M": 6,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 64000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2025-09-29",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "anthropic/claude-sonnet-4.6",
      "slug": "anthropic-claude-sonnet-4-6",
      "name": "Anthropic: Claude Sonnet 4.6",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "description": "Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...",
      "inputPer1M": 3,
      "outputPer1M": 15,
      "blendedPer1M": 6,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-02-17",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "fireworks/ember-1",
      "slug": "fireworks-ember-1",
      "name": "Fireworks: Ember-1",
      "provider": "fireworks",
      "providerName": "Fireworks",
      "description": "Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...",
      "inputPer1M": 3,
      "outputPer1M": 15,
      "blendedPer1M": 6,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-09-24",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "google/gemini-4-neon",
      "slug": "google-gemini-4-neon",
      "name": "Google: Gemini 4 Neon",
      "provider": "google",
      "providerName": "Google",
      "description": "Gemini 4 Neon is a fast, mid-priced model in the Gemini 4 family from Google, built for coding and agentic work. It is suited for repository and terminal coding, web...",
      "inputPer1M": 3,
      "outputPer1M": 15,
      "blendedPer1M": 6,
      "imagePer1K": 0.003,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "audio",
        "file",
        "image",
        "text",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "flagship",
      "createdAt": "2026-11-18",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "perplexity/sonar-pro",
      "slug": "perplexity-sonar-pro",
      "name": "Perplexity: Sonar Pro",
      "provider": "perplexity",
      "providerName": "Perplexity",
      "description": "Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API...",
      "inputPer1M": 3,
      "outputPer1M": 15,
      "blendedPer1M": 6,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 200000,
      "maxCompletionTokens": 8000,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2025-03-07",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "perplexity/sonar-pro-search",
      "slug": "perplexity-sonar-pro-search",
      "name": "Perplexity: Sonar Pro Search",
      "provider": "perplexity",
      "providerName": "Perplexity",
      "description": "Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...",
      "inputPer1M": 3,
      "outputPer1M": 15,
      "blendedPer1M": 6,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 200000,
      "maxCompletionTokens": 8000,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2025-10-30",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "qwen/qwen3.8-max-prime",
      "slug": "qwen-qwen3-8-max-prime",
      "name": "Qwen: Qwen3.8 Max Prime",
      "provider": "qwen",
      "providerName": "Qwen",
      "description": "Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...",
      "inputPer1M": 4,
      "outputPer1M": 12,
      "blendedPer1M": 6,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 131072,
      "inputModalities": [
        "text",
        "image",
        "video"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": true,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-09-23",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-4o-2024-05-13",
      "slug": "openai-gpt-4o-2024-05-13",
      "name": "OpenAI: GPT-4o (2024-05-13)",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...",
      "inputPer1M": 5,
      "outputPer1M": 15,
      "blendedPer1M": 7.5,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 128000,
      "maxCompletionTokens": 4096,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2024-05-13",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "anthropic/claude-opus-5.5",
      "slug": "anthropic-claude-opus-5-5",
      "name": "Anthropic: Claude Opus 5.5",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "description": "Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...",
      "inputPer1M": 4,
      "outputPer1M": 20,
      "blendedPer1M": 8,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-09-22",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "~anthropic/claude-opus-latest",
      "slug": "anthropic-claude-opus-latest",
      "name": "Anthropic: Claude Opus Latest",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "description": "This model always redirects to the latest model in the Claude Opus family.",
      "inputPer1M": 4,
      "outputPer1M": 20,
      "blendedPer1M": 8,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-04-21",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "meta/muse-wonder",
      "slug": "meta-muse-wonder",
      "name": "Meta: Muse Wonder",
      "provider": "meta",
      "providerName": "Meta",
      "description": "Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...",
      "inputPer1M": 4,
      "outputPer1M": 20,
      "blendedPer1M": 8,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1048576,
      "maxCompletionTokens": 943718,
      "inputModalities": [
        "text",
        "image",
        "video",
        "file",
        "audio"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": true,
      "tier": "flagship",
      "createdAt": "2026-10-12",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.6-sol",
      "slug": "openai-gpt-5-6-sol",
      "name": "OpenAI: GPT-5.6 Sol",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...",
      "inputPer1M": 4,
      "outputPer1M": 20,
      "blendedPer1M": 8,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-07-09",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.6-sol-pro",
      "slug": "openai-gpt-5-6-sol-pro",
      "name": "OpenAI: GPT-5.6 Sol Pro",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
      "inputPer1M": 4,
      "outputPer1M": 20,
      "blendedPer1M": 8,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-07-09",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.4-image-2",
      "slug": "openai-gpt-5-4-image-2",
      "name": "OpenAI: GPT-5.4 Image 2",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding,...",
      "inputPer1M": 8,
      "outputPer1M": 15,
      "blendedPer1M": 9.75,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 272000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "image",
        "text",
        "file"
      ],
      "outputModalities": [
        "image",
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-04-21",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "anthropic/claude-opus-4.5",
      "slug": "anthropic-claude-opus-4-5",
      "name": "Anthropic: Claude Opus 4.5",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "description": "Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...",
      "inputPer1M": 5,
      "outputPer1M": 25,
      "blendedPer1M": 10,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 200000,
      "maxCompletionTokens": 64000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2025-11-24",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "anthropic/claude-opus-4.6",
      "slug": "anthropic-claude-opus-4-6",
      "name": "Anthropic: Claude Opus 4.6",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "description": "Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...",
      "inputPer1M": 5,
      "outputPer1M": 25,
      "blendedPer1M": 10,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-02-04",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "anthropic/claude-opus-4.7",
      "slug": "anthropic-claude-opus-4-7",
      "name": "Anthropic: Claude Opus 4.7",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "description": "Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...",
      "inputPer1M": 5,
      "outputPer1M": 25,
      "blendedPer1M": 10,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-04-16",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "anthropic/claude-opus-4.8",
      "slug": "anthropic-claude-opus-4-8",
      "name": "Anthropic: Claude Opus 4.8",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "description": "Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...",
      "inputPer1M": 5,
      "outputPer1M": 25,
      "blendedPer1M": 10,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-05-27",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "anthropic/claude-opus-5",
      "slug": "anthropic-claude-opus-5",
      "name": "Anthropic: Claude Opus 5",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "description": "Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...",
      "inputPer1M": 5,
      "outputPer1M": 25,
      "blendedPer1M": 10,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-07-24",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5-image",
      "slug": "openai-gpt-5-image",
      "name": "OpenAI: GPT-5 Image",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior inst...",
      "inputPer1M": 10,
      "outputPer1M": 10,
      "blendedPer1M": 10,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 400000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "image",
        "text",
        "file"
      ],
      "outputModalities": [
        "image",
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2025-10-14",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-chat-latest",
      "slug": "openai-gpt-chat-latest",
      "name": "OpenAI: GPT Chat Latest",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...",
      "inputPer1M": 5,
      "outputPer1M": 30,
      "blendedPer1M": 11.25,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 400000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-05-05",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.5",
      "slug": "openai-gpt-5-5",
      "name": "OpenAI: GPT-5.5",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...",
      "inputPer1M": 5,
      "outputPer1M": 30,
      "blendedPer1M": 11.25,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-04-24",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "sakana/fugu-ultra",
      "slug": "sakana-fugu-ultra",
      "name": "Sakana: Fugu Ultra",
      "provider": "sakana",
      "providerName": "Sakana",
      "description": "Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...",
      "inputPer1M": 5,
      "outputPer1M": 30,
      "blendedPer1M": 11.25,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-06-24",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "sakana/fugu-ultra-v2",
      "slug": "sakana-fugu-ultra-v2",
      "name": "Sakana: Fugu Ultra v2",
      "provider": "sakana",
      "providerName": "Sakana",
      "description": "Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...",
      "inputPer1M": 5,
      "outputPer1M": 30,
      "blendedPer1M": 11.25,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-09-11",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "anthropic/claude-fable-5.2",
      "slug": "anthropic-claude-fable-5-2",
      "name": "Anthropic: Claude Fable 5.2",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "description": "Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible...",
      "inputPer1M": 8,
      "outputPer1M": 40,
      "blendedPer1M": 16,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-11-09",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "~anthropic/claude-fable-latest",
      "slug": "anthropic-claude-fable-latest",
      "name": "Anthropic: Claude Fable Latest",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "description": "This model always redirects to the latest model in the Claude Fable family.",
      "inputPer1M": 8,
      "outputPer1M": 40,
      "blendedPer1M": 16,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-06-09",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "~openai/gpt-astra-latest",
      "slug": "openai-gpt-astra-latest",
      "name": "OpenAI: GPT Astra Latest",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "This model always redirects to the latest model in the GPT Astra family.",
      "inputPer1M": 8,
      "outputPer1M": 40,
      "blendedPer1M": 16,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-09-11",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-6.2-astra",
      "slug": "openai-gpt-6-2-astra",
      "name": "OpenAI: GPT-6.2 Astra",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-6.2 Astra is the flagship model in the GPT-6.2 series from OpenAI, built for the hardest projects. It is suited for real-world engineering, professional work and scientific research, with stronger...",
      "inputPer1M": 8,
      "outputPer1M": 40,
      "blendedPer1M": 16,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-11-17",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-6.2-astra-pro",
      "slug": "openai-gpt-6-2-astra-pro",
      "name": "OpenAI: GPT-6.2 Astra Pro",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-6.2 Astra Pro is the same underlying model as [GPT-6.2 Astra](https://openrouter.ai/openai/gpt-6.2-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
      "inputPer1M": 8,
      "outputPer1M": 40,
      "blendedPer1M": 16,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-11-17",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "anthropic/claude-fable-5",
      "slug": "anthropic-claude-fable-5",
      "name": "Anthropic: Claude Fable 5",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "description": "Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...",
      "inputPer1M": 10,
      "outputPer1M": 50,
      "blendedPer1M": 20,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-06-09",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "anthropic/claude-fable-5.1",
      "slug": "anthropic-claude-fable-5-1",
      "name": "Anthropic: Claude Fable 5.1",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "description": "Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...",
      "inputPer1M": 10,
      "outputPer1M": 50,
      "blendedPer1M": 20,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1000000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-09-01",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-6-astra",
      "slug": "openai-gpt-6-astra",
      "name": "OpenAI: GPT-6 Astra",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...",
      "inputPer1M": 10,
      "outputPer1M": 50,
      "blendedPer1M": 20,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-09-04",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-6-astra-pro",
      "slug": "openai-gpt-6-astra-pro",
      "name": "OpenAI: GPT-6 Astra Pro",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
      "inputPer1M": 10,
      "outputPer1M": 50,
      "blendedPer1M": 20,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-09-04",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "anthropic/claude-opus-4.1",
      "slug": "anthropic-claude-opus-4-1",
      "name": "Anthropic: Claude Opus 4.1",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "description": "Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...",
      "inputPer1M": 15,
      "outputPer1M": 75,
      "blendedPer1M": 30,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 200000,
      "maxCompletionTokens": 32000,
      "inputModalities": [
        "image",
        "text",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2025-08-05",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/o3-pro",
      "slug": "openai-o3-pro",
      "name": "OpenAI: o3 Pro",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...",
      "inputPer1M": 20,
      "outputPer1M": 80,
      "blendedPer1M": 35,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 200000,
      "maxCompletionTokens": 100000,
      "inputModalities": [
        "text",
        "file",
        "image"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": true,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2025-06-10",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-4",
      "slug": "openai-gpt-4",
      "name": "OpenAI: GPT-4",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...",
      "inputPer1M": 30,
      "outputPer1M": 60,
      "blendedPer1M": 37.5,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 8191,
      "maxCompletionTokens": 4096,
      "inputModalities": [
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": false,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2023-05-28",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5-pro",
      "slug": "openai-gpt-5-pro",
      "name": "OpenAI: GPT-5 Pro",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...",
      "inputPer1M": 15,
      "outputPer1M": 120,
      "blendedPer1M": 41.25,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 400000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "image",
        "text",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2025-10-06",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.2-pro",
      "slug": "openai-gpt-5-2-pro",
      "name": "OpenAI: GPT-5.2 Pro",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...",
      "inputPer1M": 21,
      "outputPer1M": 168,
      "blendedPer1M": 57.75,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 400000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "image",
        "text",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2025-12-10",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.4-pro",
      "slug": "openai-gpt-5-4-pro",
      "name": "OpenAI: GPT-5.4 Pro",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...",
      "inputPer1M": 30,
      "outputPer1M": 180,
      "blendedPer1M": 67.5,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "text",
        "image",
        "file"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-03-05",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    },
    {
      "id": "openai/gpt-5.5-pro",
      "slug": "openai-gpt-5-5-pro",
      "name": "OpenAI: GPT-5.5 Pro",
      "provider": "openai",
      "providerName": "OpenAI",
      "description": "GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...",
      "inputPer1M": 30,
      "outputPer1M": 180,
      "blendedPer1M": 67.5,
      "imagePer1K": null,
      "requestCost": 0,
      "contextLength": 1050000,
      "maxCompletionTokens": 128000,
      "inputModalities": [
        "file",
        "image",
        "text"
      ],
      "outputModalities": [
        "text"
      ],
      "isFree": false,
      "isOpenWeight": false,
      "isReasoning": false,
      "supportsVision": true,
      "supportsAudio": false,
      "tier": "flagship",
      "createdAt": "2026-04-24",
      "lastSeenAt": "2026-11-21T19:54:45.261Z",
      "source": "openrouter"
    }
  ]
}
