Mistral Large 3 (675B Instruct 2512)

by Mistral AI

Mistral Large 3 (675B Instruct 2512) is a model from Mistral AI, released on December 4, 2025. It has a 262K-token context window and can generate up to 262K output tokens. API pricing is $0.5 per 1M input tokens and $1.5 per 1M output tokens.

Mistral Large 3 (675B Instruct 2512) is a state-of-the-art general-purpose Multimodal granular Mixture-of-Experts model with 41B active parameters and 675B total parameters trained from scratch with 3000 H200s. This model is the instruct post-trained version in FP8, fine-tuned for instruction tasks, making it ideal for chat, agentic and instruction based use cases. A no-loss FP8 version to reduce resource requirements. Can be deployed on a node of B200s or H200s. Designed for reliability and long-context comprehension - It is engineered for production-grade assistants, retrieval-augmented systems, scientific workloads, and complex enterprise workflows.

Key specs

ProviderMistral AI
Release date2025-12-04
Licenseopen source
Context window262K tokens
Max output262K tokens
Input price$0.5 / 1M tokens
Output price$1.5 / 1M tokens
Intelligence Score9
Coding index1.4
Output speed122 tokens/s
Time to first token3.49 s

Quick answers

What is the context window of Mistral Large 3 (675B Instruct 2512)?

Mistral Large 3 (675B Instruct 2512) has a context window of 262K tokens, with a maximum output of 262K tokens per response.

How much does Mistral Large 3 (675B Instruct 2512) cost?

Mistral Large 3 (675B Instruct 2512) costs $0.5 per 1M input tokens and $1.5 per 1M output tokens through the API.

Is Mistral Large 3 (675B Instruct 2512) open source?

Yes. Mistral Large 3 (675B Instruct 2512) is an open model released under the open source license.

When was Mistral Large 3 (675B Instruct 2512) released?

Mistral AI released Mistral Large 3 (675B Instruct 2512) on December 4, 2025.

Compare on the AI leaderboard · All AI models

More models from Mistral AI