token.app › Mistral AI › Mistral Medium 3
Mistral Medium 3 pricing & benchmarks
Mistral Medium 3 is available from Mistral AI at $0.400 per million input tokens and $2.00 per million output tokens ($0.800 blended at 3:1). It accepts up to 131,072 tokens of context. 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× lowe…
Pricing
Per million tokens · OpenRouter
Input$0.400
Output$2.00
Blended (3:1)$0.800
Specification
mistralai/mistral-medium-3
Context window131K
Max output105K
ReleasedMay 2025
LicenceProprietary
Modalitiesin:text, in:image, in:file, out:text
Benchmarks
Independently run — not vendor self-reports. Every score links its source.
| Benchmark | Score | Config | Run | Source |
|---|---|---|---|---|
| GPQA Diamond | 59.5% ±2.8 | — | 2025-05-07 | Independently run · Epoch AI |
| OTIS Mock AIME | 32.2% ±6.0 | — | 2025-05-07 | Independently run · Epoch AI |
Scores published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0.
Cheaper models that score at least as well on GPQA Diamond
Strictly lower blended price AND an equal-or-higher GPQA Diamond score. One benchmark is one dimension — a model that wins here may still be weaker at your specific task.
| Model | Provider | Blended $/1M | GPQA Diamond | |
|---|---|---|---|---|
| gpt-oss-20b | OpenAI | $0.036 (−96%) | 60.8% | Compare → |
| Qwen3.7 Flash | Alibaba | $0.055 (−93%) | 82.3% | Compare → |
| Qwen3.5-Flash | Alibaba | $0.114 (−86%) | 82.3% | Compare → |
| GPT-5 Nano | OpenAI | $0.138 (−83%) | 69.4% | Compare → |
| Gemma 4 31B | $0.250 (−69%) | 75.8% | Compare → |
Where to run Mistral Medium 3
3 options across 1 provider · 1.1× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Uptime 24h |
|---|---|---|---|---|
| Mistral (zdr) | $0.800 | $0.400 / $2.00 | 131K | 100.0% |
| Mistral | $0.800 | $0.400 / $2.00 | 131K | 100.0% |
| Mistral (eu) | $0.880 | $0.440 / $2.20 | 131K | 100.0% |
Host prices and uptime from OpenRouter, synced 2026-10-22.
Compare Mistral Medium 3
FAQ
How much does Mistral Medium 3 cost?
Mistral Medium 3 costs $0.400 per million input tokens and $2.00 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.800 per million tokens.
What is Mistral Medium 3's context window?
Mistral Medium 3 accepts up to 131,072 tokens of context, and can generate up to 104,857 output tokens.
How good is Mistral Medium 3 on benchmarks?
Mistral Medium 3 scores 59.5% on GPQA Diamond, independently run and published by Epoch AI. 2 benchmark results are listed on this page, each with its run date and source.
Is there a cheaper model as good as Mistral Medium 3?
Yes — 5 models in our catalogue cost less per token than Mistral Medium 3 and score at least as high on the same benchmark. The cheapest is gpt-oss-20b at $0.036 per million tokens blended.