Mistral Large 3
by OpenRouter · family mistral-large · listed Dec 2025TVW
Flagship Mistral model for advanced reasoning, coding, and multilingual work
Current rates USD per 1M tokens
Input$0.50
Output$1.50
Cache read$0.05
Cache write—
Against the market
On the record
- Model id
mistralai/mistral-large-2512- Context window
- 262K tokens
- Max output
- 210K tokens
- Input modalities
- text, image, pdf
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Nov 2024
- Released
- 2025-12-02
- Last updated
- 2025-12-02
- Provider docs
- openrouter.ai/models
Back of the envelope
≈
Also listed at
- LLM Gateway$0.50 in · $1.50 out
- Kilo Gateway$0.50 in · $1.50 out
- Merge Gateway$0.50 in · $1.50 out
- Opper$0.50 in · $1.50 out
- Eden AI$0.50 in · $1.50 out
- Tempr Gateway$0.50 in · $1.50 out
- Mistral$0.50 in · $1.50 out
- DevPass (LLM Gateway)$0.50 in · $1.50 out
- Cortecs$0.613 in · $1.84 out
- 302.AI$1.10 in · $3.30 out
- AnyAPI— in · — out