As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/cohere-embed-v4/

# Cohere Embed v4

Cohere, Embed family. Status: current. Type: embedding model. Released: 2025-04.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Cohere API | `embed-v4.0` | https://api.cohere.com/v2/embed | https://docs.cohere.com/docs/cohere-embed |
| AWS Bedrock | `cohere.embed-v4:0` |  | https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-cohere-embed-v4.html |

## Pricing

- Price not published.
- Last checked: 2026-09-29

## Specs

- Input: text, image, pdf
- Output: text
- Context window: 128,000 tokens
- Max output: not published
- Open weights: no
- Licence: proprietary

## Where it stands

- Newer embedding models in the registry since its release: 5:
  - EmbeddingGemma 2 (2026-10-06) https://postcutoff.com/m/embeddinggemma-2/
  - Cohere Embed 5 Fast (2026-09-30) https://postcutoff.com/m/cohere-embed-v5-fast/
  - Cohere Embed 5 Pro (2026-09-30) https://postcutoff.com/m/cohere-embed-v5-pro/
  - Gemini Embedding 2 (2026-04-22) https://postcutoff.com/m/gemini-embedding-2/
  - Cohere Rerank 4 (Pro / Fast) (2025-12-11) https://postcutoff.com/m/cohere-rerank-4/
- After it from Cohere: Cohere Rerank 4 (Pro / Fast) (2025-12-11) https://postcutoff.com/m/cohere-rerank-4/
- Closed weights; access is hosted only.

## What stands out

- Interleaved text+image (PDF) embeddings: Embeds text, images and mixed text/image documents such as PDFs into one vector space. Source: https://docs.cohere.com/docs/cohere-embed
- 128K-token input with Matryoshka dims: Up to 128K tokens per input; output dimension selectable 256/512/1024/1536. Source: https://docs.cohere.com/docs/models

## Notes

Output is vectors (modality_out text used as placeholder). Release month (Apr 2025) from memory, not re-verified. Pricing not verified (Cohere pricing page shows only Model Vault hourly rates).

Multimodal embeddings for search/RAG over long docs and scanned PDFs.

```bash
curl https://api.cohere.com/v2/embed -H "Authorization: Bearer $CO_API_KEY" -H "Content-Type: application/json" \
 -d '{"model":"embed-v4.0","input_type":"search_document","embedding_types":["float"],"texts":["hello world"]}'
```

Sources: https://docs.cohere.com/docs/models , https://docs.cohere.com/docs/cohere-embed

Model page: https://postcutoff.com/m/cohere-embed-v4/