Mistral Small 4
AvailableSource-backed identifier on the Mistral API. Unverified details are marked below.
Access details: Mistral API
Versioned identifier · Identity and lifecycle apply to this exact identifier and serving surface.
mistral-small-2603Capabilities & limits
- Context window
- 256K
- Maximum output
- Not verified
- Image input
- Supported
- Tool calling
- Supported
- Structured output
- Supported
Documented interfaces and limits. These are not measures of model quality.
Pricing
USD / 1M tokens- Input
- $0.15Derived from the captured rate card's standard token row.
- Output
- $0.60Derived from the captured rate card's standard token row.
USD per million standard text tokens. Detailed cache, batch and other pricing conditions appear in the rate card.
Full rate card 2 rates
Amounts in USD. Check the unit and conditions on each rate.
Input
$0.15 per 1M tokensOutput
$0.60 per 1M tokensPrice history
Input $0.15 per million tokens
Derived from the captured rate card's standard token row.
Output $0.60 per million tokens
Derived from the captured rate card's standard token row.
Technical details
- Parameters
- 119B
- Active parameters
- 6.5B
- Architecture
- hybrid instruct, reasoning, and coding
- Input modalities
- text, image
- Output modalities
- text
1 detail not verified
- Training / knowledge cutoff
From Mistral AI
Official announcement link: not verified yet.
How they describe it
Our powerful hybrid model unifying instruct, reasoning, and coding capabilities in a single model.
What they say is different
Provider quote not captured yet.
Verbatim provider claims · not an independent assessment
Release & lifecycle
Availability applies to this exact identifier on Mistral API.
- First API availability
- Mar 16, 2026
- available
- Observed Sep 13, 2026