Mistral
France's frontier lab, with the small models everyone self-hosts.
Mistral is the main model family from the French lab of the same name, and it splits in a way worth knowing about: the Small models publish their weights so you can download and run them, while Medium and Large are sold through the API only. Small 4 folds several older models into one and is cheap enough to use by default; Medium 3.5 is the one to reach for on agentic and coding work. Mistral's other lines are separate products with their own names — Devstral and Codestral for code, Ministral for tiny on-device models, and Voxtral for speech, which has its own entry here.
At a glance — Mistral Large 3 2512
- Cost
- $0.50 in · $1.50 out per 1M tokensBudget
- Memory
- 262K tokens — about 400 pages
- Reads
- Text · Images · Files
- Can do
- Use tools (agents)
- Structured output
- Thinking mode (not supported)
- Good at
- Coding: better than 16% · Agentic work: better than 12% · Overall: better than 10%
- Reliability
- 99.96% uptime, last 24h
- Released
- Dec 1, 2025
Advanced details
- API model ID
mistralai/mistral-large-2512- Max output
- 210K tokens
- Cached input
- $0.05 per 1M
- Tokenizer
- Mistral
- Coding index
- 20.1
- Agentic work index
- 1.0
- Overall index
- 9.3
Providers
The same model, hosted by different companies. OpenRouter picks one per request and falls back to the next if it fails.
| Provider | Input /1M | Output /1M | Cached /1M | Max output | Uptime 24h |
|---|---|---|---|---|---|
| Mistral · zdr | $0.50 | $1.50 | $0.05 | 210K | 99.76% |
| Mistral · eu | $0.55 | $1.65 | $0.055 | 210K | 99.96% |
Supported parameters
- frequency_penalty
- max_tokens
- presence_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_p
Live from OpenRouter, refreshed hourly. Scores from Artificial Analysis.
Key info
- Pricing
- Freemium
- Category
- Models
- Best for
- Intermediate
- Made by
- Mistral AI, in France
- Weights
- Open for Small and Nemo, closed for Medium and Large
- Good for
- A cheap default model, and EU-hosted inference