Mistral's latest flagship model with 675B parameters and MoE architecture.
LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.
S
Mistral's latest flagship model with 675B parameters and MoE architecture. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for Mistral Large 3 on LLM Gateway starts at $0.50 per million input tokens and $1.50 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
Mistral Large 3 supports a context window of up to 262,144 tokens on its largest provider deployment.
Mistral Large 3 is served by OpenRouter, Mistral AI through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
Yes. Mistral Large 3 supports both tool (function) calling and structured JSON outputs through LLM Gateway.
Mistral Large 3 was released on December 2, 2025.
Devstral 2
262,144 context$0.40 in / $2.00 out per 1M
Mistral Large Latest
128,000 context$4.00 in / $12.00 out per 1M
Ministral 14B
262,144 context$0.20 in / $0.20 out per 1M
Ministral 8B
262,144 context$0.15 in / $0.15 out per 1M
Ministral 3B
131,072 context$0.10 in / $0.10 out per 1M
Codestral
256,000 context$0.30 in / $0.90 out per 1M