Mistral · Embedding model

Codestral Embed 2505

mistralai/codestral-embed-2505

Embedding

Released Oct 30, 2025

Mistral Codestral Embed is specially designed for code, perfect for embedding code databases, repositories, and powering coding assistants with state-of-the-art retrieval.

Specifications

Input: text
Output: vector per input (float array; base64 on request)
Batch: up to 512 inputs per call
Billing: per input token

Use it

POST /api/v1/embeddings · MCP embed · full reference

curl https://omnirail.org/api/v1/embeddings \
  -H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
  -d '{"model":"mistralai/codestral-embed-2505","input":["brass lever espresso machine","coffee grinder"]}'