Cohere - API - verified
Embed 4 embeddings
Embed 4 is a current embedding model from Cohere, called by API as embed-v4.0. It returns 1,536-dimension vectors by default and accepts up to 128,000 input tokens, for text, image and PDF input. No per-1M-token list price is stated for it. cohere.com/pricing shows no self-serve per-token rate for Embed 4 today.
CurrentModel id: embed-v4.0
- Default dims
- 1,536
- Max input
- 128,000 tok
- Price / 1M
- Not stated
- Inputs
- Text, Image, PDF
Dimensions
Flexible output size- 1,536default
- 1,024
- 512
- 256
Default output: 1,536 dimensions.
Listed sizes: 1,536, 1,024, 512 and 256.
Cohere documents shorter output vectors for this model (Matryoshka-style), so you can store smaller embeddings by asking for fewer dimensions instead of re-embedding with another model.
Pricing
- Per 1M input tokens
- Not stated
- Batch, per 1M
- Not stated
cohere.com/pricing shows no self-serve per-token rate for Embed 4 today.
Source: cohere.com/pricing
Usage
The sources read for this directory publish no copyable snippet for Embed 4. Call it with the model id embed-v4.0 as shown in the provider docs linked under Sources.
Worth knowing
Produces unified embeddings from mixed text and image payloads such as PDF pages, and Cohere named it a replacement when Embed v2.0 was retired on April 4, 2026.
Release date not stated in the sources. Multilingual: not stated.
FAQ
How many dimensions does Embed 4 output?
Default output: 1,536 dimensions. Listed sizes: 1,536, 1,024, 512 and 256. Cohere documents shorter output vectors for this model (Matryoshka-style), so you can store smaller embeddings by asking for fewer dimensions instead of re-embedding with another model.
What is the max input length of Embed 4?
128,000 tokens per input, per Cohere's documentation. Longer text has to be chunked before you embed it.
How much does Embed 4 cost?
No per-1M-token list price is stated for it. cohere.com/pricing shows no self-serve per-token rate for Embed 4 today. Source: https://cohere.com/pricing.
What can Embed 4 embed?
Text, image and PDF input, per the provider.
Sources
Last verified from the pages below.
- Cohere Embed models - docs.cohere.com
- Cohere Embed v4 announcement - docs.cohere.com
- Cohere release notes - docs.cohere.com
More Cohere embedding models
Default dimensions, max input tokens and list price per 1M tokens.
- Embed 5 Pro2,048 dims - 128,000 tokens - $0.12
- Embed 5 Fast2,048 dims - 128,000 tokens - $0.08
- Embed English v3.01,024 dims - 512 tokens - Not stated
- Embed English Light v3.0384 dims - 512 tokens - Not stated
- Embed Multilingual v3.01,024 dims - 512 tokens - Not stated
- Embed Multilingual Light v3.0384 dims - 512 tokens - Not stated
Newsletter
New models, every week
One email per week. New model releases, embedding and retrieval updates and what they mean for what you build.
Keep exploring
Model API pricing and specs
First-party prices per 1M tokens for chat and reasoning models.
Local models
Open-weight LLMs you can download and run, with sizes and licenses.
What is RAG?
Where embeddings fit in a retrieval pipeline, end to end.
Vector databases compared
Where the vectors go once you have picked a model.