Mistral Small
Mistral Small first-party. Strong cost/latency for general chat.
mistral/mistral-small-latest
- Context
- 128k tokens
- Completion cap
- —
- Tools
- Yes
- JSON
- Yes
Call it from Geek Hub
Same OpenAI SDK. Change the base URL and the model id.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistral/mistral-small-latest",
"messages": [{"role": "user", "content": "Hola"}]
}'Frequently asked questions
- What is Mistral Small?
- Mistral Small first-party. Strong cost/latency for general chat. Mistral Small runs on the Geek Hub API (OpenAI-compatible). Model id: mistral/mistral-small-latest.
- Is Mistral Small free?
- No. Input is $0.109 per 1M tokens and output is $0.327 per 1M tokens on Geek Hub (markup included).
- What is the context length of Mistral Small?
- Mistral Small has a 128k tokens context window.
- Does Mistral Small support tool calling and structured outputs?
- Mistral Small accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.