# Embed 5 Pro

> Cohere Embed 5 Pro is the higher-accuracy tier of Cohere's Embed 5 family (about 2.4B parameters). It turns text into 2048-dimension vectors for search and RAG across more than 100 languages, with a 128K-token context. Embed 5 Pro and Fast share one vector space, so an index built with one can be queried with the other.

**ID**: `cohere/embed-5-pro`  
**Creator**: Cohere  
**Category**: embedding  
**Context**: 128K tokens  
**Pricing**: $0.12 / $0 per 1M · billed by your provider (BYOK)  
**Released**: 2026-09-30  
**Web page**: https://anyrouter.dev/model/cohere/embed-5-pro

**Input modalities**: text  
**Output modalities**: embeddings  

**Capabilities**: embedding

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/embeddings`

```bash
curl https://anyrouter.dev/api/v1/embeddings \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "cohere/embed-5-pro",
  "input": "The quick brown fox jumps over the lazy dog"
}'
```

Pass `input` as a string or an array of strings to embed a batch in one call.

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| cohere-byok | $0.12/M (list) | $0 (list) |
| nousresearch-byok | $0.12/M (list) | $0 (list) |

BYOK routes are billed by your own provider key — AnyRouter charges $0. Rates marked (list) are the provider's published list price.

## Model card

- Native context: 128000 tokens [1]

### Strengths [2,1]

- Over 100 languages and a 128K-token context (vendor-stated).
- Shares one vector space with the other Embed 5 tier (vendor-stated).

### Links

- announcement: https://cohere.com/blog/embed-5
- docs: https://docs.cohere.com/docs/cohere-embed

### Sources

1. [Cohere Embed docs](https://docs.cohere.com/docs/cohere-embed) (accessed 2026-11-06)
2. [Introducing Embed 5](https://cohere.com/blog/embed-5) (accessed 2026-11-06)

## Source

- Upstream docs: https://docs.cohere.com/docs/cohere-embed