Cyberax AI Playbook
cyberax.com
Model · Cohere · Embeddings

Cohere Embed 5

Cohere's flagship embedding family (embed-v5.0-pro, embed-v5.0-fast). Multimodal (text, images, mixed text+image documents such as PDFs) with 128K context, 100+ languages, Matryoshka dimensions and int8/binary embeddings — useful for cost-sensitive RAG.

Modality
Embeddings
License
Proprietary (Proprietary)
Context window
128,000 tokens
Released
September 30, 2026
Last verified
October 28, 2026
Runs locally
No

Strengths

  • Multimodal (text, image, and fused text+image) embeddings in one model
  • Pro and Fast tiers share one embedding space — index with one, query with the other
  • Matryoshka dimensions (256-2048) plus int8/binary formats cut storage cost
  • 100+ languages; available on Microsoft Foundry and Amazon SageMaker, or self-hosted via vLLM in private deployments

Weaknesses

  • Closed weights
  • Cost and index size grow if you actually use the full 128K context

Try it

WhereTypeNotes
Cohere API hosted-api API key required
AWS Bedrock hosted-api Enterprise; lists Embed 4, not Embed 5 (checked 2026-10-28)

Used in solutions

Change log

  • — Updated from Embed v4 to Embed 5 (released 2026-09-30): embed-v5.0-pro and embed-v5.0-fast, 128K context, dimensions 256-2048 (default 2048), text/image/mixed inputs, 100+ languages; API price per Cohere's announcement $0.12 (Pro) / $0.08 (Fast) per 1M text tokens. embed-v4.0 is still listed on Cohere's models page. AWS Bedrock does not list Embed 5 yet; the announcement names Microsoft Foundry and Amazon SageMaker.
  • — 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.