All Models

Mistral Large 3

mistral-large Tool Calling Attachments Open Weights Structured Output

Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.

Providers 8
Released Nov 1, 2024
Input Modalities text, image, pdf
Output Modalities text
Tarsk Use coding

Benchmarks

15.9
Intelligence Index
20.1
Coding Index
38
Math Index

Available Providers (8)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Vercel AI Gateway mistral/mistral-large-3 $0.50/MTok $1.50/MTok 256K 256K
Mistral mistral-large-2512 $0.50/MTok $1.50/MTok 262.1K 262.1K
Merge Gateway mistral/mistral-large-2512 $0.50/MTok $1.50/MTok 262.1K 262.1K
LLM Gateway mistral-large-2512 $0.50/MTok $1.50/MTok 262.1K 262.1K
Amazon Bedrock mistral.mistral-large-3-675b-instruct $0.50/MTok $1.50/MTok 256K 8.2K
OpenRouter mistralai/mistral-large-2512 $0.50/MTok $1.50/MTok 262.1K 262.1K
routing.run route/mistral-large-3 $0.50/MTok $1.50/MTok 128K 32.8K
AnyAPI mistralai/mistral-large-2512 —/MTok —/MTok 262.1K 262.1K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output