Back to Models
mistralai logoMistral
mistralai/devstral-medium
Not Available

Devstral Medium

Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Positioned as a step up from Devstral Small, it achieves 61.6% on SWE-Bench Verified, placing it ahead of Gemini 2.5 Pro and GPT-4.1 in code-related tasks, at a fraction of the cost. It is designed for generalization across prompt styles and tool use in code agents and frameworks. Devstral Medium is available via API only (not open-weight), and supports enterprise deployment on private infrastructure, with optional fine-tuning capabilities.

7/10/2025
131,072 tokens

Specifications

Modalities

Input
text
Output
text

Supported Parameters

frequency_penalty
max_tokens
presence_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_p

Data policy

Prompt retention
Unknown — we could not confirm
Training
Unknown — not declared

"Unknown" does not mean "safe". It means we could not confirm it.

Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.

Frequently asked questions

Is Devstral Medium available on FastMetal?
Not at the moment. Voxtral Mini 3B, from the same lab, is available on the FastMetal API today.
What is the context window of Devstral Medium?
131,072 tokens, shared between the prompt and the response.