Skip to content
Mistral

Mistral Large 3

flagship
Mistral · released 2025-03-01 · text
currently routing · 4.2k rpm
128M tokens
Context
— / 1M
Input
— / 1M
Output
— t/s
Speed
open
License
/ ABOUT

Mistral Large 3 is the flagship model in Mistral AI's lineup, delivering top-tier performance across reasoning, coding, multilingual understanding, and instruction following. As the most capable Mistral model, it competes with other frontier models on major benchmarks while offering Mistral's characteristic efficiency.

The model supports a large context window and handles complex multi-step tasks including advanced coding, mathematical reasoning, nuanced creative writing, and sophisticated analysis. It features strong tool-use capabilities for agentic workflows and multimodal understanding for processing images alongside text.

Mistral Large 3 is recommended for the most demanding AI applications where quality cannot be compromised, serving as the premium option in Mistral's model portfolio.

BENCHMARKS Artificial Analysis Index
Intelligence 23

Providers for Mistral Large 3

4 routes · sorted by uptime

ClosedRouter routes requests to the providers best able to handle your prompt size and parameters, with automatic fallbacks to maximize uptime.

Provider
Context
Quant
Uptime · 30d
bf16
0.00%
bf16
0.00%
bf16
0.00%
bf16
0.00%