Devstral Small

Devstral Small is a legacy model from Mistral AI, retained for compatibility with older integrations. It belongs to the devstral line, which also includes Devstral Medium. It has a context window of 128000 tokens and a maximum output of 128000 tokens. The weights are open. It supports tool calling but not reasoning mode. It accepts text and returns text. Pricing starts at $0.10 per million input tokens and $0.30 per million output tokens. It is served by 2 hosts.

First version of its line in the registry.

• ·128k token context window
• ·128k token max output
• ·Open weights for self-hosting
• ·Supports tool calling
• ·Low input price at $0.10 per million

• Reach for it for compatibility with existing integrations
• Reach for it for large-context text generation
• Reach for it for tool-calling workflows
• Reach for it for cost-sensitive text processing

2 hosts serve this model at the price above · the maker's documentation

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window and max output?

Both the context window and the maximum output are 128000 tokens.

Does it support tool calling and reasoning?

It supports tool calling, but it does not have a reasoning mode.

Is the model open weights and what is the price?

Yes, the weights are open. Pricing starts at $0.10 per million input tokens and $0.30 per million output tokens.