Cohere Embed v4
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).
- Context window
- 128,000 tokens
- Input
- text, image, pdf
- Output
- text
- License
- proprietary
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| Cohere API | embed-v4.0 | https://api.cohere.com/v2/embed | docs |
| AWS Bedrock | cohere.embed-v4:0 | — | docs |
Notable capabilities (2)
- Interleaved text+image (PDF) embeddings: Embeds text, images and mixed text/image documents such as PDFs into one vector space. source
- 128K-token input with Matryoshka dims: Up to 128K tokens per input; output dimension selectable 256/512/1024/1536. source
Multimodal embeddings for search/RAG over long docs and scanned PDFs.
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
Other Cohere models
Command A+ · Cohere Rerank 4 (Pro / Fast) · Command A (03-2025) and variants