Models / Mistral AI
LLM
Chat

Mistral

7.3B model surpassing Llama 2 13B, nearing CodeLlama 7B on code, with GQA for speed and SWA for efficient long-sequence handling.

This model is not available on Together’s Serverless API.

Pick a supported alternative from the Model Library.

Related models
new
Chat
DeepSeek V4 Pro

  • Cached/1M

    $0.20

  • Input/1M

    $1.74

  • Output/1M

    $3.48
Function Calling
JSON Mode
Reasoning
Chat
Code
LLM
new
Chat
MiniMax M3

  • Cached/1M

    $0.06

  • Input/1M

    $0.30

  • Output/1M

    $1.20
Function Calling
JSON Mode
Reasoning
Vision
Chat
new
Chat
Kimi K2.7 Code

  • Cached/1M

    $0.19

  • Input/1M

    $0.95

  • Output/1M

    $4.00
Function Calling
JSON Mode
Vision
Chat
Code
LLM
Model specifications
Model data
  • Model provider
    Mistral AI
  • Type
    LLM
    Chat
  • Main use cases
    Chat
    Small & Fast
  • Parameters
    7B
  • Context length
    8192
  • Quantization level
    FP16
  • Category
    Chat