NVIDIA: Nemotron 3 Super API Pricing & Cost Breakdown
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...
nvidia/nemotron-3-super-120b-a12b
Technical Specifications
| Canonical ID | nvidia/nemotron-3-super-120b-a12b |
| Provider | NVIDIA |
| Input Modalities | text |
| Output Modalities | text |
| Open-Weight | No (Proprietary API) |
| Reasoning Optimized | Standard |
| Vision Support | Text-only |
Estimated Monthly API Spend
| Stage | Monthly Tokens | Est. Cost |
|---|---|---|
| Prototype / MVP 500 req/day |
22.5M in / 6.0M out | $4.09/mo |
| Growing SaaS 10,000 req/day |
600.0M in / 150.0M out | $105.00/mo |
| Scale Production 100,000 req/day |
7500.0M in / 1800.0M out | $1,283/mo |
Deploy or Route NVIDIA: Nemotron 3 Super
OpenRouter
Unified API gateway for 300+ LLMs with automatic fallbacks and unified billing.
Together AI
High-throughput serverless inference & fine-tuning for Llama, DeepSeek, and Qwen.
GroqCloud
LPU-accelerated inference delivering hundreds of tokens per second for real-time voice & agents.
Some outbound infrastructure and API gateway links on KostoZero are partner referrals that help keep this observatory free and independent at no extra cost to you.
Cheaper Alternatives to NVIDIA: Nemotron 3 Super
| Model | Provider | Input / 1M | Output / 1M | Blended | Context |
|---|---|---|---|---|---|
| Mistral: Voxtral Small 24B 2507 | Mistral AI | $0.10 | $0.30 | $0.15 | 33K |
| Qwen: Qwen3 14B | Qwen | $0.12 | $0.24 | $0.15 | 41K |
| Qwen: Qwen3 30B A3B Instruct 2507 | Qwen | $0.10 | $0.30 | $0.15 | 262K |
| Ricursive: Ripple 65B Preview | Ricursiveai | $0.10 | $0.30 | $0.15 | 1.05M |
| Z.ai: GLM 4.7 Flash | Z Ai | $0.06 | $0.40 | $0.145 | 200K |
| Tencent: Hy3 | Tencent | $0.083 | $0.33 | $0.144 | 262K |
Frequently Asked Questions
How much does NVIDIA: Nemotron 3 Super API cost per 1M tokens?
NVIDIA: Nemotron 3 Super costs $0.075 per 1M input tokens and $0.40 per 1M output tokens ($0.156 blended at a 3:1 ratio).
What is the maximum context window of NVIDIA: Nemotron 3 Super?
NVIDIA: Nemotron 3 Super supports up to 262,144 tokens (262K) of input context and up to 16,384 output completion tokens.
What are cheaper alternatives to NVIDIA: Nemotron 3 Super?
Lower-cost options tracked right now include Mistral: Voxtral Small 24B 2507 ($0.15/1M), Qwen: Qwen3 14B ($0.15/1M), Qwen: Qwen3 30B A3B Instruct 2507 ($0.15/1M).
Get Instant Price-Drop (>10%), New AI Bot & SaaS Cliff Alerts
Every 6 hours our autonomous sync checks 40+ LLMs, AI crawlers, and SaaS pricing cliffs—alerting you when prices drop >10% or new scrapers appear.