Providers and ModelsMistral AI

Magistral Medium 2509 Thinking

Magistral Medium 2509 Thinking
Mistral AI · Text Generation
POST /v1/chat/completions

Reasoning model tuned for tasks needing longer thought and higher accuracy: legal research, financial forecasting, software, and storytelling.

This model is deprecated and will be retired on 2026-07-31. After that date, requests to this model will fail. Migrate to a successor model before then.

At a glance

FieldValue
Model idmagistral-medium-2509-thinking
Input modalitiesText
Output modalitiesText
Context window40K
Weight precision-
Max output tokens40,000
Features-
Native inferenceNo
NewNo
Supported endpointsPOST /v1/chat/completions, POST /v1/responses, POST /v1/messages
Deprecation date2026-07-31

Pricing

ChargeSpecRate
Inputper 1M prompt tokens$2.60
Outputper 1M generated tokens$6.50
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": "magistral-medium-2509-thinking", "messages": [{"role":"user","content":"Hello"}]}'

Parameters

ParameterTypeRequiredDefaultDescription
temperaturenumberno0.7Sampling temperature · Range: 0 – 2
top_pnumberno1.0Nucleus sampling · Range: 0 – 1
max_tokensnumberno4096Max output tokens · Range: 1 – 65536
frequency_penaltynumberno0Penalty for repeated tokens. >0 reduces repetition, <0 encourages it. · Range: -2 – 2
presence_penaltynumberno0Penalty for new vs. seen tokens. >0 encourages new topics, <0 encourages staying on topic. · Range: -2 – 2
stopstringno-Comma-separated stop sequences
include_reasoningbooleannotrueWhen true, the response includes the model’s reasoning trace alongside the final answer.
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 a flat $0.013 per request on top of the model’s normal token cost. Disabled by default.
disable_formattingbooleannofalseWhen enabled, the gateway will not append the “Sources” footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.

Notes

Standard Magistral Medium 2509 chat parameters. No separate thinking budget is exposed.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/magistral-medium-2509-thinking.