Mistral Medium 3.5
Mistral · Released 28 Apr 2026 · mistral-medium-3-5
$1.50
Input price / 1M tokens
#34 of 61, cheapest first
$7.50
Output price / 1M tokens
#35 of 61, cheapest first
256K
Context window
#59 of 71
169
Output tokens / second
#16 of 61
77.6%
SWE-bench Verified
#4 of 12
Summary
Mistral Medium 3.5 is an open-weight model from Mistral, released on 28 Apr 2026.
At $1.50 input and $7.50 output per million tokens, it is #34 of 61 on input price, cheapest first.
Its 256K-token context window ranks #59 of 71.
Measured output speed is 169 tokens per second, #16 of 61.
Mistral's flagship merged model: a 128B dense open-weight model that combines instruction following, reasoning and coding, with configurable reasoning effort and image input. Mistral recommends it for most tasks and coding.
Benchmarks · 2 reported
| Benchmark | Score | Bar | Rank | Source |
|---|---|---|---|---|
| SWE-bench Verified | 77.6% | #4 of 12 | Mistral launch postSelf-reported | |
| τ³-Bench Telecomreported as "91.4 on τ³-Telecom" | 91.4% | – | Mistral launch postSelf-reported |
Self-reported means the lab ran the test itself. A rank appears only where several labs report the same version of a benchmark.
Similar models
Models with the most benchmarks in common with Mistral Medium 3.5, and the closest scores.
SWE-bench Verified
#4 of 12Real GitHub issues, fixed and tested
- Mistral Medium 3.577.6
- Claude Sonnet 4.577.2
- Gemini 3 Flash78
- Kimi K2.680.2
- GPT-574.9
- Gemini 3.1 Pro80.6
Compare Mistral Medium 3.5 side by side
Pre-filled with the two closest models. Swap any of them.
Sources
- API ID, version 26.04, date, license, context, price: docs.mistral.ai/models/mistral-medium-3-5-26-04, checked 2 Oct 2026
- cached input price: docs.mistral.ai/inference/pricing, checked 2 Oct 2026
- batch discount, free plan API credits: mistral.ai/pricing, checked 2 Oct 2026
- free mode API usage: docs.mistral.ai/admin/billing-usage/usage-limits, checked 2 Oct 2026
- 128B dense, open weights, image input, benchmarks: mistral.ai/news/vibe-remote-agents-mistral-medium-3-5, checked 2 Oct 2026
- model lineup and deprecations: docs.mistral.ai/getting-started/models/, checked 2 Oct 2026
- output speed: artificialanalysis.ai/models/mistral-medium-3-5, checked 2 Oct 2026
Building on Mistral Medium 3.5?
Get the architecture right before the bill arrives.
We size caching, routing and fallbacks for your workload on a free call, and tell you where a cheaper model is good enough.