Mistral Large
A large language model released by Mistral, with a focus on cybersecurity capabilities. The model was trained in Mistral's own European data centers using 3,800 NVIDIA Grace Blackwell chips.
Timeline (last 90 days)
In Mistral's past product line, open weights typically fell on small- and medium-scale models such as Mistral 7B and Mixtral 8x7B, while the Large series was mainly offered as commercial API services.
Mistral built community reputation through open-weight models such as Mistral 7B and Mixtral, while the Large series is the pillar of its commercialization revenue.
The Mistral Large series is offered only via API, without public weights.
The Mistral Large series focuses on multilingual capabilities, long-context processing and complex reasoning, targeting enterprise-level API usage scenarios.
Mistral AI takes "open + efficient" as its differentiated route, has accumulated a high reputation in the open-source community, and the Large series plays the role of competing head-on with frontier closed-source models such as GPT and Claude.
The Odysseus application running locally does not mean the model also runs locally; when a cloud model (such as Mistral Large) is selected, data leaves the local machine and is routed through OpenRouter to Mistral's API.
The Mistral Large series is positioned as a high-performance flagship model.
Mistral Large was trained in European data centers using 3,800 NVIDIA Grace Blackwell chips, with model weights and license to be published by the end of the month.
Mistral has released its next-generation Large model, now available for public preview with direct API access.
All Facts (9)
In Mistral's past product line, open weights typically fell on small- and medium-scale models such as Mistral 7B and Mixtral 8x7B, while the Large series was mainly offered as commercial API services.
50%UnverifiedMistral built community reputation through open-weight models such as Mistral 7B and Mixtral, while the Large series is the pillar of its commercialization revenue.
50%UnverifiedThe Mistral Large series is offered only via API, without public weights.
50%UnverifiedThe Mistral Large series focuses on multilingual capabilities, long-context processing and complex reasoning, targeting enterprise-level API usage scenarios.
50%UnverifiedMistral AI takes "open + efficient" as its differentiated route, has accumulated a high reputation in the open-source community, and the Large series plays the role of competing head-on with frontier closed-source models such as GPT and Claude.
50%UnverifiedThe Odysseus application running locally does not mean the model also runs locally; when a cloud model (such as Mistral Large) is selected, data leaves the local machine and is routed through OpenRouter to Mistral's API.
50%UnverifiedThe Mistral Large series is positioned as a high-performance flagship model.
50%UnverifiedMistral Large was trained in European data centers using 3,800 NVIDIA Grace Blackwell chips, with model weights and license to be published by the end of the month.
50%UnverifiedMistral has released its next-generation Large model, now available for public preview with direct API access.
50%