Embed 5 Fast

cohere/embed-v5.0-fast

An embedding model with a 128K-token context window, at $0.084 per million tokens.

Details

Maker: cohere
Kind: Embeddings
Context window: 128,000 tokens
Input: $0.084 per million tokens
Capabilities: None listed
Takes: Text
Returns: Text
Zero data retention: Not on every provider
No training on requests: Yes, on every provider
Released: 2026-09-30

Description

Cohere's lightweight embedding model optimized for low latency and high throughput in interactive search, agent loops, and high-volume retrieval. Embed 5 Fast supports text, images, and mixed content, over 100 languages, and a 128,000-token context window, with output dimensions from 256 to 2,048. It shares an embedding space with Embed 5 Pro.

Call it

curl

curl https://phantom.codes/v1/embeddings \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "cohere/embed-v5.0-fast",
    "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