Mistral Medium 3.5
mistral-medium-3.5
Open SourceMultimodal
About
Mistral Medium 3.5 is Mistral AI's first flagship merged model, combining instruction-following, reasoning, coding, and vision in one dense 128B model. It supports configurable reasoning effort, text and image input, native function calling, JSON output, and a 256K context window. Released as open weights under Mistral's Modified MIT license, it can be self-hosted on as few as four H100/H200 GPUs and scores 77.6% on SWE-bench Verified.
Mistral Medium 3.5 has a 256K-token context window.
Mistral Medium 3.5 input tokens at $1.5/1M, output at $7.5/1M.
Capabilities
VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution
Providers(1)
| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| Mistral AI Studio | $1.50 | $7.50 | Serverless |
Benchmark Scores(1)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| SWE-bench Verified | 77.6 | SWE-bench Verified | https://mistral.ai/news/vibe-remote-agents-mistral-medium-3-5 |
Rankings
Best LLMs for Code GenerationBest AI Agents & Agentic ModelsBest Open Source LLMsBest Multimodal / Vision LLMsBest LLMs for Reasoning & MathBest LLMs for Function Calling & Tool UseCheapest LLM APIsBest LLM APIsBest LLMs for EnterpriseBest Free LLMsBest LLMs for WritingBest LLMs for MarketingBest LLMs for Customer Support
Specifications
FamilyMistral Medium
Released2026-04-29
Parameters128B
Context256K
ArchitectureDecoder Only
Specializationgeneral
LicenseMistral License
Trainingpretrained
