Codestral Embed

mistral/codestral-embed

An embedding model with a 131K-token context window, at $0.1575 per million tokens.

Details

Maker: mistral
Kind: Embeddings
Context window: 131,072 tokens
Input: $0.1575 per million tokens
Cached input: $0.01575 per million tokens, 90% off
Cache write: Same as input
Capabilities: None listed
Takes: Text
Returns: Text
Zero data retention: Yes, on every provider
No training on requests: Yes, on every provider
Released: 2025-05-28

Description

Code embedding model that can embed code databases and repositories to power coding assistants.

Call it

curl

curl https://phantom.codes/v1/embeddings \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral/codestral-embed",
    "input": "The quick brown fox"
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model