The Orchestrator › Models › Mistral AI
Mistral AI: Mistral Large 3
Mistral Large 3 2512 is Mistral’s most capable model to date. It has a sparse mixture-of-experts architecture with 41B active parameters (675B total).
Specifications
| Provider | Mistral AI |
| Model ID | mistralai/mistral-large-3 |
| Context window | 262K tokens (262,144) |
| Modalities | text + image → text |
| Tokenizer | — |
| Router sources | Vercel AI Gateway |
| Released | 2025-12-02 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | Vercel AI Gateway | mistralai/mistral-large-3 | $0.5 | $1.50 | 262K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.5 | $1.50 | 262K |
Capabilities
Vision (image input)Agentic tool useStructured outputs256K+ context windowZero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
max_tokens, temperature, stop, tools, tool_choice, response_format, structured_outputs