Skip to navigation
Authors and ModelsMistral AI

Mistral Small 3.1

Mistral Small 3.1
Mistral AI · Text Generation
POST /v1/chat/completions

24B-parameter multimodal model with 128K context for image analysis, programming, math, and multilingual tasks, tuned for efficient local inference.

At a glance

FieldValue
Model idmistral-small-3-1
Model release date2025-03-17
Input modalitiesText, Image
Output modalitiesText
Context window128K
Weight precision-
Max output tokens32,768
Featuresvision, function_calling
Native inferenceNo
NewNo
Structured outputJSON Schema
Supported endpointsPOST /v1/chat/completions, POST /v1/responses, POST /v1/messages, POST /v1beta/models/mistral-small-3-1:generateContent
Alternate model idsmistral-small-3.1, mistralai/mistral-small-3.1

Pricing

ChargeSpecRate
Per Messagefixed$0.0019
Web Search (Linkup)per call when invoked$0.013

Example request

curl https://api.empiriolabs.ai/v1/chat/completions \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "mistral-small-3-1", "messages": [{"role":"user","content":"Hello"}]}'

Parameters

ParameterTypeRequiredDefaultDescription
temperaturenumberno0.15Sampling temperature. 0 = deterministic, 5 = maximum randomness. · Range: 0 – 5
top_pnumberno1.0Nucleus sampling probability mass. Lower = more focused. · Range: 0.01 – 1
max_tokensnumberno4096Maximum tokens in the response. · Range: 1 – 32768
toolsstringno-OpenAI-format tool definitions
tool_choicestringno-auto, none, required, or {type, function}
response_formatenumno-Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide.
web_search_linkupbooleannofalseOptional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model’s normal token cost. Disabled by default.
disable_formattingbooleannofalseReturn the answer without the Sources list that web search adds.

Notes

Input is limited to about 500,000 characters per request.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/mistral-small-3-1.