Model · Cohere · Embeddings
Cohere Embed v4
Cohere's flagship embedding model (embed-v4.0). Multimodal (text + image) with up to 128K context; strong multilingual coverage and compressed (int8/binary) embeddings — useful for cost-sensitive RAG.
- Modality
- Embeddings
- License
- Proprietary (Proprietary)
- Context window
- 128,000 tokens
- Released
- April 15, 2025
- Last verified
- September 8, 2026
- Runs locally
- No
Strengths
- Multimodal (text + image) embeddings in one model (v4)
- Compressed-embedding support (int8, binary) cuts storage cost
- Strong multilingual retrieval performance; available via AWS Bedrock
Weaknesses
- Closed weights
- Cost and index size grow if you actually use the full 128K context
Try it
| Where | Type | Notes |
|---|---|---|
| Cohere API | hosted-api | API key required |
| AWS Bedrock | hosted-api | Enterprise |
Used in solutions
Official sources
- Embed docs docs
Change log
- — Verified current against Cohere's models page. embed-v4.0 is still the newest Embed generation; everything below is v3.0/v2.0. No v5 exists.
- — Updated from Embed v3 to embed-v4.0 (released 2025-04-15): multimodal, 128K context. The v3.0 models remain available but are no longer the flagship.
- — Initial entry.
Esc