Cohere Embed 5 Fast
Embedding model
embed-v5.0-fast
$0.08 in per 1M tokens
Second-stage reranking for RAG and enterprise search.
Model idrerank-v4.0-pro
PricePrice not published
Checked29 September 2026
4newer embedding models since its release
3 ways to use Cohere Rerank 4 (Pro / Fast), with the model id each provider expects.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Cohere API | rerank-v4.0-pro |
https://api.cohere.com/v2/rerank |
docs.cohere.com |
| Cohere API (fast) | rerank-v4.0-fast |
https://api.cohere.com/v2/rerank |
|
| OpenRouter | cohere/rerank-4-pro |
openrouter.ai |
Price not published.
No price source linked. Checked 29 September 2026.
What its maker marketed at launch, and what people found later, each with its source.
Rerank window grew from 4K (v3.5) to 32K tokens, so whole long documents can be scored.
Two variants: pro for best accuracy, fast for latency-sensitive search.
Reranker (scores query-document relevance). Previous: rerank-v3.5 (Bedrock cohere.rerank-v3-5:0).
curl https://api.cohere.com/v2/rerank -H "Authorization: Bearer $CO_API_KEY" -H "Content-Type: application/json" \
-d '{"model":"rerank-v4.0-pro","query":"capital of France","documents":["Paris is the capital of France.","Berlin is in Germany."]}'
Sources: https://docs.cohere.com/docs/models
Not yet checked against an official source: Release date from third-party listing; pricing not verified (OpenRouter ~$0.0025/search reported, not checked).