Reasoning model tuned for tasks needing longer thought and higher accuracy: legal research, financial forecasting, software, and storytelling.
Mistral AIText Generation40K contextProprietary EndpointReasoning model tuned for tasks needing longer thought and higher accuracy: legal research, financial forecasting, software, and storytelling.
magistral-medium-2509-thinkingPOST /v1/chat/completionsPOST /v1/responsesPOST /v1/messagesLive pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.
Magistral Medium 2509 Thinking serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id magistral-medium-2509-thinking. Get an API key from the EmpirioLabs dashboard.
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": "Write a haiku about the ocean."}
]
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.empiriolabs.ai/v1",
api_key="YOUR_EMPIRIOLABS_API_KEY",
)
response = client.chat.completions.create(
model="magistral-medium-2509-thinking",
messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)Request parameters supported by the Magistral Medium 2509 Thinking API on EmpirioLabs. Defaults apply when a field is omitted.
| Parameter | Type | Default | Range / values | Description |
|---|---|---|---|---|
| temperature | number | 0.7 | 0 to 2 | Sampling temperature |
| top_p | number | 1 | 0 to 1 | Nucleus sampling |
| max_tokens | number | 4096 | 1 to 65536 | Max output tokens |
| frequency_penalty | number | 0 | -2 to 2 | Penalty for repeated tokens. >0 reduces repetition, <0 encourages it. |
| presence_penalty | number | 0 | -2 to 2 | Penalty for new vs. seen tokens. >0 encourages new topics, <0 encourages staying on topic. |
| stop | string | - | - | Comma-separated stop sequences |
| include_reasoning | boolean | true | - | When true, the response includes the model's reasoning trace alongside the final answer. |
| web_search_linkup | boolean | false | - | Optional 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... |
| disable_formatting | boolean | false | - | When 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... |
Standard Magistral Medium 2509 chat parameters. No separate thinking budget is exposed.
On EmpirioLabs, Magistral Medium 2509 Thinking is billed pay as you go: Input $2.60 per 1M prompt tokens; Output $6.50 per 1M generated tokens; Web Search (Linkup) $0.013 per call when invoked. The live rate card on this page always matches what the API charges.
Magistral Medium 2509 Thinking supports a 40K-token context window with up to 40,000 output tokens per response.
Yes. Magistral Medium 2509 Thinking serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to magistral-medium-2509-thinking.
Yes. The EmpirioLabs playground runs Magistral Medium 2509 Thinking in the browser with the same parameters the API exposes, so you can test prompts before writing code.
Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.
Explore our models, or contact us about business inquiries, custom deployments, or anything else.
