All AI models · LLM benchmarks · Methodology

Mistral

Mistral Embed

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Model facts

Context window
8K tokens
Maximum output
3K tokens
Cheapest paid input
$0.1 per 1M tokens
Cheapest paid output
free per 1M tokens
Open weights
no
Providers
2

Capabilities and modalities

temperature control, text.

Observed price history

  • 2026-08-24: $0.1 input / free output per 1M tokens

API providers

  • Mistral — model id mistral-embed; $0.1 input / free output per 1M tokens; provider documentation
  • Vercel AI Gateway — model id mistral/mistral-embed; not published input / not published output per 1M tokens; provider documentation