Pixtral 12B
API ID pixtral-12b-2409
Pixtral 12B was a Mistral model, released September 2024. It had a 128,000-token context window. It took image and PDF input and supported function calling and structured outputs.
A 12B model with image understanding capabilities in addition to text.
- Status
- Retired
- Released
- September 2024
- Shutdown
- Dec 31, 2025
- Replacement
- Ministral 3 14Bministral-14b-2512
pixtral-12b-2409 stopped serving on December 31, 2025. Recommended replacement: ministral-14b-2512.
How to migrate to Ministral 3 14B
Benchmarks
Scores as each source published themNo comparison. Pick a model to see the difference on each benchmark.
Arena
| Arena | Pixtral 12B | Rank | Date | Source |
|---|---|---|---|---|
| Vision | 1025 ±10 | 148 of 165 7,511 votes | Oct 9, 2026 | source |
Rated as pixtral-12b-2409. Ratings come from people voting between two anonymous answers; Vision is style-controlled, as on arena.ai. Data: Arena (arena.ai), CC BY 4.0.
Features
Compare models| Feature | Value | Since | Source |
|---|---|---|---|
| Structured outputsThe model can be held to a JSON schema you supply, so every reply parses without retries or cleanup. | Supported | in place when tracking began (October 6, 2026) | source |
| Function callingAlso called tool use. You describe functions; the model replies with a function name and arguments for your code to run, then uses the result. | Supported | in place when tracking began (October 6, 2026) | source |
| Batch APISend many requests as one job that runs in the background, usually finished within 24 hours, at a lower price than live requests. | Supported | in place when tracking began (October 6, 2026) | source |
| Image inputImages such as screenshots, photos and charts can go in the prompt for the model to read. | Supported | in place when tracking began (October 6, 2026) | source |
| PDF inputPDF files can go in the prompt directly, without converting them to text first. | Supported | in place when tracking began (October 6, 2026) | source |
| Context windowThe most the model can work with in one request, in tokens: your prompt, conversation history and files. A token is about three-quarters of an English word. | 128,000 tokens | in place when tracking began (October 6, 2026) | source |
Not published by Mistral: Prompt caching, Reasoning / thinking, Fine-tuning, Built-in web search, temperature parameter, top_p parameter, logprobs, Max output tokens.
Price history
USD per 1M tokens, standard tierWe started recording this model's prices on Oct 5, 2026. The history grows with each daily check.
Show as a table
| From | Type | Price |
|---|---|---|
| Oct 5, 2026 | Input | $0.15 |
| Oct 5, 2026 | Output | $0.15 |
Prices
USD per 1M tokens, every type and band, by tier| Type | Price $/1M | In effect |
|---|---|---|
| Standard | ||
| input | $0.15 | |
| output | $0.15 | |
Changelog
Changes we detected on Mistral's pagesNo changes recorded yet.
Last checked · Sources: Mistral models