Mistral AIChat

Magistral Medium 2506 (Thinking)

magistral-medium-2506:thinking

Magistral Medium 2506 (Thinking) by Mistral AI.

Context: 41.0K tokens
Endpoint

Pricing

Input$2.00 / 1M

Output$5.00 / 1M

Cache Write (5m)$2.00 / 1M

Cache Write (1h)$2.00 / 1M

Cache Read$2.00 / 1M

Web Search$0 / 1M

Quick Start

Select an endpoint and copy a working example for this model.

Endpoint

python

from openai import OpenAI client = OpenAI(    api_key="YOUR_API_KEY",    base_url="https://api.apertis.ai/v1") response = client.chat.completions.create(    model="magistral-medium-2506:thinking",    messages=[        {"role": "user", "content": "Hello!"}    ],    max_tokens=1024,    temperature=0.7) print(response.choices[0].message.content) # Optional: Enable context compression to reduce token usage# response = client.chat.completions.create(#     model="magistral-medium-2506:thinking",#     messages=[{"role": "user", "content": "Hello!"}],#     extra_body={"compression": {"enabled": True, "model": "gpt-4.1-mini"}}# )

Supported Parameters

API docs

Common7 params

modelmessagesmax_tokenstemperaturetop_pstreamtools

Extended4 params

reasoning_effortstream_optionsthinkingextra_body

Cursor IDE Model IDs

Use these namespaced identifiers in Cursor IDE to avoid conflicts with built-in models.

magistral-medium-2506:thinking

Questions about Magistral Medium 2506 (Thinking)

How much does Magistral Medium 2506 (Thinking) cost on Apertis?

Magistral Medium 2506 (Thinking) costs $2.00 per 1M input tokens and $5.00 per 1M output tokens on Apertis.

What is Magistral Medium 2506 (Thinking)'s context window?

Magistral Medium 2506 (Thinking) has a context window of 41.0K tokens.

Which company develops Magistral Medium 2506 (Thinking)?

Magistral Medium 2506 (Thinking) is developed by Mistral AI.

Which model ID do I use to call Magistral Medium 2506 (Thinking)?

Use the model ID magistral-medium-2506:thinking to call Magistral Medium 2506 (Thinking).

Compare with Other Models

See how this model compares to others from the same provider.

Voxtral Mini 3B 2507

Mistral AI Voxtral Mini (3B) speech-to-text. Billed per second of audio.

Context: N/A
Input: — (Not priced per input token)
Output: — (Not priced per output token)

Voxtral Small 24B 2507 STT

Mistral AI Voxtral Small (24B) speech-to-text. Billed per second of audio.

Context: N/A
Input: — (Not priced per input token)
Output: — (Not priced per output token)

Voxtral Small is an upgraded version of Mistral Small 3 that adds advanced audio understanding while preserving strong text performance. It handles speech transcription, translation, and audio comprehension, with audio input billed per million seconds.

Context: 32K
Input: $0.125/M
Output: $0.375/M

Mistral Small Creative

Mistral Small Creative is an experimental lightweight model focused on creative writing and storytelling. It excels at narrative generation, roleplay, character dialogue, and general instruction-following for conversational agents.

Context: 32.8K
Input: $0.10/M
Output: $0.30/M