Mistral Medium 3
by Mistral · family mistral-medium · listed May 2025TV
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
Current rates USD per 1M tokens
Input$0.40
Output$2.00
Cache read—
Cache write—
Against the market
On the record
- Model id
mistral-medium-2505- Context window
- 131K tokens
- Max output
- 131K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- May 2025
- Released
- 2025-05-07
- Last updated
- 2025-05-07
- Provider docs
- docs.mistral.ai/getting-started/models/
Back of the envelope
≈
Also listed at
- GitHub Modelsfree in · free out
- Merge Gateway$0.40 in · $2.00 out
- Azure$0.40 in · $2.00 out
- Azure Cognitive Services$0.40 in · $2.00 out
- routing.run$0.40 in · $2.00 out