MistralMistral LargeFeb 26, 2024

Mistral Large Latest

This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement here. It supports dozens of languages including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese, and Korean, along with 80+ coding languages including Python, Java, C, C++, JavaScript, and Bash. Its long context window allows precise information recall from large documents.

Context Window
131K
tokens
Max Output
tokens
Released
Feb 26, 2024
Arena Rank
Output Speed
85
tokens/sec
Time to First Token
620ms
TTFT

Capabilities

👁Vision
🧠Reasoning
🔧Tool Calling
Prompt Caching
🖥Computer Use
🎨Image Generation

Supported Parameters

Frequency Penalty
Reduce repetition
Max Tokens
Output length limit
Presence Penalty
Encourage new topics
Response Format
JSON mode / structured output
Seed
Deterministic outputs
Stop Sequences
Custom stop tokens
structured_outputs
Temperature
Controls randomness
Tool Choice
Control tool usage
Tool Calling
Function calling support
Top P
Nucleus sampling

Pricing Comparison

RouterInput / 1MOutput / 1MCached Input / 1M
Requesty$2.00$6.00$2.00
OpenRouter$2.00$6.00
Martian$2.00$6.00

Benchmarks

Artificial Analysis
Intelligence IndexArtificial Analysis
50/100
Coding IndexArtificial Analysis
45/100
Math IndexArtificial Analysis
52/100
MMLU-PROArtificial Analysis
0.685/1
GPQA DiamondArtificial Analysis
0.488/1
MATH-500Artificial Analysis
0.725/1
AIME 2024Artificial Analysis
0.083/1
LiveCodeBenchArtificial Analysis
0.395/1

Model IDs

Requestymistral/mistral-large-latest
OpenRoutermistralai/mistral-large

Tags

tool-calling
Compare with another model

Related Models