Mistral Large 3 is Mistral AI's open-weight multimodal granular Mixture-of-Experts model, with 675B total and 41B active parameters. It takes text and image input with a 256K-token context window and is built for agentic work, tool use, retrieval-augmented systems, long documents and coding across dozens of languages.
Modalities
In / out price
$0.58 / $1.75per 1M
Context
256K
Max output
32K
Updated
Nov 5, 2026
Providers
2 routesCompare providers by price, privacy, and speed.
Amazon Bedrock | Private | $0.58 | $1.75 | — | 256K | 32K | — | — |
Surplus Intelligence | Anonymous | $0.70 | $2.10 | $0.07 | 256K | 32K | — | — |
Privacy
2 / 4Private routing
Private tier
- Anonymous
- Private
- TEE
- E2EE
Prompt and response content is not retained after the request. Request content is visible to the inference runtime while it is being processed. Learn more
Features
3Streaming
Tool calling
Vision
Uptime
FAQ
Common questions about Mistral Large 3 675B Instruct.