Cohere

About Cohere

Cohere empowers every developer and enterprise to build high-impact applications with secure and scalable AI.

Website ↗Documentation ↗Hugging Face ↗

Source ↗ · 2026-11-12T02:17:03.276551062Z

53 indexed models

53 matching models

Embed 5 Fast

vercelAIGatewayCatalog/cohere/embed-v5.0-fast

Cohere's lightweight embedding model optimized for low latency and high throughput in interactive search, agent loops, and high-volume retrieval. Embed 5 Fast supports text, images, and mixed content, over 100 languages, and a 128,000-token context window, with output dimensions

Context window
128,000
Input modalities
text
Output modalities
text

Benchmarks

  • MTEB: 62.149%

Embed 5 Pro

vercelAIGatewayCatalog/cohere/embed-v5.0-pro

Cohere's most capable embedding model for quality-critical enterprise retrieval across text, images, and mixed content such as PDFs. Embed 5 Pro supports over 100 languages and a 128,000-token context window, with output dimensions from 256 to 2,048. It shares an embedding space

Context window
128,000
Input modalities
text
Output modalities
text

Benchmarks

  • MTEB: 65.866%

Embed English

awsBedrock/cohere.embed-english-v3

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Embed English

awsBedrock/cohere.embed-english-v3:0:512

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Embed Multilingual

awsBedrock/cohere.embed-multilingual-v3

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Embed Multilingual

awsBedrock/cohere.embed-multilingual-v3:0:512

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Embed v4

awsBedrock/cohere.embed-v4:0

Input modalities
text, image
Output modalities
embeddings
Capabilities
embeddings, multimodal, visionInput

embed-v4.0

cheaperInference/embed-v4.0

Context window
128,000
Output modalities
embeddings
Capabilities
embeddings, visionInput

Inference prices

Embed v4.0

vercelAIGatewayCatalog/cohere/embed-v4.0

A model that allows for text, images, or mixed content to be classified or turned into embeddings.

Context window
128,000
Input modalities
text
Output modalities
text

Benchmarks

  • MTEB: 65.433%

embed-v5.0-fast

cheaperInference/embed-v5.0-fast

Context window
128,000
Output modalities
embeddings
Capabilities
embeddings

Inference prices

embed-v5.0-pro

cheaperInference/embed-v5.0-pro

Context window
128,000
Output modalities
embeddings
Capabilities
embeddings

Inference prices

Rerank 3.5

awsBedrock/cohere.rerank-v3-5:0

Input modalities
text
Output modalities
text

rerank-v3.5

cheaperInference/rerank-v3.5

Context window
4,096
Maximum output
4,096

rerank-v4-fast

cheaperInference/rerank-v4-fast

Context window
32,000
Maximum output
32,000
Capabilities
reranking

rerank-v4-pro

cheaperInference/rerank-v4-pro

Context window
32,000
Maximum output
32,000
Capabilities
reranking

rerank-v5-fast

cheaperInference/rerank-v5-fast

Context window
32,768
Maximum output
32,768
Capabilities
reranking

Inference prices

rerank-v5-pro

cheaperInference/rerank-v5-pro

Context window
32,768
Maximum output
32,768
Capabilities
reranking

Inference prices

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace