Post-Cutoff

CohereEmbed familyCurrentEmbedding modelReleased 30 Sep 2026

Cohere Embed 5 Pro

Model idembed-v5.0-pro

Price$0.12 in per 1M tokens

Checked1 October 2026

Where it stands

1newer embedding model since its release

All embedding models

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

How to call it

4 ways to use Cohere Embed 5 Pro, with the model id each provider expects.

Providers, model ids, endpoints and docs for Cohere Embed 5 Pro
ProviderModel idEndpointDocs
Cohere API embed-v5.0-pro https://api.cohere.com/v2/embed docs.cohere.com
Microsoft Foundry
Amazon SageMaker
Cohere Model Vault

Pricing

Prices for Cohere Embed 5 Pro
Input$0.12 per 1M tokens

As published: “per 1M text tokens (images $0.40 per 1M tokens)”.

Source: cohere.com, checked 1 October 2026.

Specs

Input
Text and images
Output
Text
Context window
128,000 tokens
Max output
Not published
Open weights
No
Licence
Proprietary
Released
30 September 2026
Status
Current
Type
Embedding model

What stands out

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

  • Shared embedding space across tiers

    Embed 5 Pro and Fast vectors are interoperable: index with Pro, query with Fast without re-indexing.

    Source: docs.cohere.com

  • Multimodal 128K embeddings

    Text, image and fused text+image input, 100+ languages, Matryoshka dims 256-2048.

    Source: docs.cohere.com

Notes

Highest-quality tier for offline indexing; ViDoRe V3 85.8 (Cohere). 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-v5.0-pro","input_type":"search_query","embedding_types":["float"],"texts":["hello world"]}'

Not yet checked against an official source: Bedrock/Foundry model ids not verified.