Eliminating the 4 Hidden Taxes: AI Tokens, Manual Work, SaaS Cliffs & AI Scrapers Sponsor this header →

Mistral: Devstral 2 2512 API Pricing & Cost Breakdown

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...

mistralai/devstral-2512
budget
Last checked: Nov 21, 2026
Input / 1M Tokens
$0.40
Prompt & context tokens
Output / 1M Tokens
$2.00
Generated completion tokens
Blended (3:1) / 1M
$0.80
Tier: budget
Context Window
262K
Max output: 210K

Technical Specifications

Canonical IDmistralai/devstral-2512
ProviderMistral AI
Input Modalitiestext, file
Output Modalitiestext
Open-WeightNo (Proprietary API)
Reasoning OptimizedStandard
Vision SupportText-only

Estimated Monthly API Spend

StageMonthly TokensEst. Cost
Prototype / MVP
500 req/day
22.5M in / 6.0M out $21.00/mo
Growing SaaS
10,000 req/day
600.0M in / 150.0M out $540.00/mo
Scale Production
100,000 req/day
7500.0M in / 1800.0M out $6,600/mo
Simulate Custom Volume → Cut Cost via 3-Tier Cascade →

Deploy or Route Mistral: Devstral 2 2512

Multi-Provider Gateway

OpenRouter

Unified API gateway for 300+ LLMs with automatic fallbacks and unified billing.

Call via OpenRouter →
Open-Weight Inference

Together AI

High-throughput serverless inference & fine-tuning for Llama, DeepSeek, and Qwen.

Run on Together AI →
Low-Latency Engine

Fireworks AI

Ultra-low-latency inference engine built for production structured outputs and function calling.

Deploy on Fireworks →

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 Mistral: Devstral 2 2512

ModelProviderInput / 1MOutput / 1MBlendedContext
Qwen2.5 Coder 32B Instruct Qwen $0.66 $1.00 $0.745 33K
Z.ai: GLM 4.7 Z Ai $0.40 $1.75 $0.738 205K
Meta: Llama 3.1 70B Instruct Meta Llama $0.72 $0.72 $0.72 131K
Meta: Llama 3.3 70B Instruct Meta Llama $0.71 $0.71 $0.71 131K
Google: Gemma 2 27B Google $0.65 $0.65 $0.65 8K
TheDrummer: Skyfall 36B V2 Thedrummer $0.55 $0.80 $0.613 33K

Frequently Asked Questions

How much does Mistral: Devstral 2 2512 API cost per 1M tokens?

Mistral: Devstral 2 2512 costs $0.40 per 1M input tokens and $2.00 per 1M output tokens ($0.80 blended at a 3:1 ratio).

What is the maximum context window of Mistral: Devstral 2 2512?

Mistral: Devstral 2 2512 supports up to 262,144 tokens (262K) of input context and up to 209,715 output completion tokens.

What are cheaper alternatives to Mistral: Devstral 2 2512?

Lower-cost options tracked right now include Qwen2.5 Coder 32B Instruct ($0.745/1M), Z.ai: GLM 4.7 ($0.738/1M), Meta: Llama 3.1 70B Instruct ($0.72/1M).

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.