Post-Cutoff
Search For AI agents

CohereEmbed familyCurrentEmbedding modelReleased Apr 2025

Cohere Embed v4

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

Model idembed-v4.0

PricePrice not published

Checked29 September 2026

Where it stands

5newer embedding models since its release

All embedding models

After it from Cohere
Cohere Rerank 4 (Pro / Fast)11 Dec 2025
Weights
Closed weights; access is hosted only.

How to call it

2 ways to use Cohere Embed v4, with the model id each provider expects.

Providers, model ids, endpoints and docs for Cohere Embed v4
ProviderModel idEndpointDocs
Cohere API embed-v4.0 https://api.cohere.com/v2/embed docs.cohere.com
AWS Bedrock cohere.embed-v4:0 docs.aws.amazon.com

Pricing

Price not published.

No price source linked. Checked 29 September 2026.

Specs

Input
Text, images and PDF
Output
Text
Context window
128,000 tokens
Max output
Not published
Open weights
No
Licence
Proprietary
Released
April 2025
Status
Current
Type
Embedding model

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Interleaved text+image (PDF) embeddings

    Embeds text, images and mixed text/image documents such as PDFs into one vector space.

    Source: docs.cohere.com

  • 128K-token input with Matryoshka dims

    Up to 128K tokens per input; output dimension selectable 256/512/1024/1536.

    Source: docs.cohere.com

Notes

Output is vectors (modality_out text used as placeholder).

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

Not yet checked against an official source: Release month (Apr 2025) from memory, not re-verified. Pricing not verified (Cohere pricing page shows only Model Vault hourly rates).