Model registry / Mistral AI / Devstral / Devstral Small 2
Devstral Small 2
Legacy model retained for compatibility with older integrations
Line
Devstral
Weights
Open
Released
2025-12-09
Context
256K
Input
$0.00 / 1M
Output
$0.00 / 1M
Max output
256K
Coverage
not covered yet
Overview
Devstral Small 2 is a legacy model from Mistral AI, retained for compatibility with older integrations. It is part of the devstral line. It has a context window of 256,000 tokens and a maximum output of 256,000 tokens. The model has open weights, supports tool calling, and accepts image and text inputs, returning text. It is priced at $0.00 per million input and output tokens. It does not support reasoning mode.
Specs
Pricing
Against Devstral Small: window 128K to 256K, input $0.10 to $0.00, output $0.30 to $0.00.
Strengths
- Open weights for self-hosting
- Supports tool calling
- Accepts both image and text inputs
- 256k token context window
- 256k token max output
Best for
- Reach for it for maintaining older integrations
- Reach for it for processing long documents with image and text
- Reach for it for tool-calling workflows
- Reach for it for zero-cost inference
How to access
1 host serve this model at the price above · the maker's documentation
Devstral: every version
The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.
FAQ
- Is this model free to use?
- Yes, it is priced at $0.00 per million input and output tokens.
- Does it support image inputs?
- Yes, it accepts image and text inputs and returns text.
- What is the context window?
- It has a context window of 256,000 tokens and a maximum output of 256,000 tokens.