whichllm — Browse and compare AI model specs and pricing

Mistral

Mistral Embed model ID, context window & pricing

mistral-embed

Quick facts

Model ID mistral-embed
Source Mistral
Context Window 8000
Pricing $0.10 input / - output per 1M tokens
Capabilities -

Model overview

Mistral Embed is an AI model from Mistral with 8000 token context window and text input support.

Published pricing is $0.10 input and - output per 1M tokens.

  • Workloads that use text inputs with text outputs.
Model ID mistral-embed
Provider Mistral
Family mistral-embed
Status -
Knowledge Cutoff -
Release Date 2023-12-11
Input Modalities text
Output Modalities text
Context Window 8000
Input Limit -
Output Limit 3072
Tool Calling No
Reasoning No
Structured Output -
Temperature Control No
Open Weights No
Input Cost / 1M tokens $0.10
Output Cost / 1M tokens -
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens -
Cache Write Cost / 1M tokens -