Mistral: Pixtral 12B
Analysis Summary
Mistral: Pixtral 12B sits in the Legacy tier on our leaderboard, ranked #392 of 565 published models on overall intelligence. At $0.100 input and $0.100 output per 1M tokens, it is among the most expensive on the market. It offers a mid-sized context window and supports vision.
Editorial notes
Mistral Pixtral 12B is a compact vision-capable model from Mistral with no intelligence benchmarks in this listing, suited to lightweight image-and-text tasks at low cost.
Assessed May 31, 2026
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Mistral: Pixtral 12B compares
Its 33K-token context window is larger than 32% of the models we list. At $0.10 per million input tokens it is cheaper than 66% of comparable models.
About Mistral: Pixtral 12B
The first multi-modal, text+image-to-text model from Mistral AI. Its weights were launched via torrent: https://x.com/mistralai/status/1833758285167722836.
Capabilities
How does Mistral: Pixtral 12B stack up?
Compare side-by-side with other legacy models.
Model Information
| OpenRouter ID |
mistralai/pixtral-12b
|
| Provider | mistralai |
| Release Date | September 10, 2024 |
| Context Length | 32,768 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.10 | $0.000100 |
| Output | $0.10 | $0.000100 |
Leaderboard Categories
External Resources
Explore Related Models
Frequently asked questions about Mistral: Pixtral 12B
How much does Mistral: Pixtral 12B cost?
Mistral: Pixtral 12B costs $0.10 per million input tokens and $0.10 per million output tokens.
What is the context window of Mistral: Pixtral 12B?
Mistral: Pixtral 12B has a context window of 32,768 tokens (33K).
What can Mistral: Pixtral 12B do?
Mistral: Pixtral 12B supports image/vision input.
Who created Mistral: Pixtral 12B?
Mistral: Pixtral 12B is developed by Mistral and was released on September 10, 2024.
Data sourced from OpenRouter API, Artificial Analysis and Hugging Face Open LLM Leaderboard. Scores are editorially curated by our team.
Last updated: June 1, 2026 8:38 pm