Embed 5 Pro

Embedding modelCard summarized

Our most capable embedding model, for text and images

Source: Embed 5 launch post and Embed models docs (no model card published)

Use it via API

$0.12 / 1M tok

Code example Compare

Where to call it

Cohere APIembed-v5.0-pro
Microsoft Foundry / Azure—

Supports

Image input

Full feature support

Good for

Offline indexing where retrieval quality matters most
Complex, visually rich or multimodal corpora (PDF pages, charts, scans)
Financial and enterprise document search

Overview

Cohere · 02Pro

Embed 5 Pro

Our most capable embedding model, for text and images

Typical price

$0.12 / 1M tok

Text input

Dimensions: 2048
Max input: 128K tokens
Modes: text embeddings, image embeddings
Released: 30 Sep 2026

Cohere · 02Pro

Embed 5 Pro

embed-v5.0-pro

Inputs: Text, Images
License: Proprietary
Outputs: Text
Price options: 3

Text input$0.12 / 1M tok
Image input$0.40 / 1M tok
Model Vault, Small instance$3.00 / hour

From the model card

Offline indexing where retrieval quality matters most
Complex, visually rich or multimodal corpora (PDF pages, charts, scans)
Behind Gemini on several languages
Migrating from Embed 4

Embed 5 Pro is one of two tiers in Cohere's Embed 5 family. Pro is the quality tier, aimed at offline indexing and complex or multimodal corpora. Both tiers embed text, images and fused text-image inputs into one shared space, so a corpus indexed with Pro can be queried with Fast. They support 100+ languages, a 128K-token context, Matryoshka dimensions from 256 to 2048, and float, int8 and binary outputs. launch post; models docs

embed-v5.0-pro

Typical price: $0.12 / 1M tok
Dimensions: 2048 (default; can be shortened to 1536, 1024, 768, 512 or 256)
Max input: 128K tokens
Languages: 100+ languages
Weights: Closed
Released: 30 Sep 2026

text embeddings
image embeddings
multimodal embeddings (fused text + image, e.g. PDF pages)