mistral-medium-3-5@eu
by Requesty · family mistral-medium · listed Apr 2026RTV
Mistral Medium 3.5 is a dense 128B instruction following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex multi step reasoning. It is particularly strong at reliable multi tool calling and long horizon tasks, with a 256K context window, configurable reasoning effort per request, and a custom vision encoder that handles variable image sizes and aspect ratios. Self hostable on as few as four GPUs and available under open weights.
Current rates USD per 1M tokens
Input$1.49
Output$7.42
Cache read$1.49
Cache write—
Against the market
On the record
- Model id
mistral-medium-3-5@eu- Context window
- 262K tokens
- Max output
- 262K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-04-30
- Last updated
- 2026-04-30
- Provider docs
- requesty.ai/solution/llm-routing/models
Back of the envelope
≈