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

Cohere Embed v3 Multilingual · azureml-cohere v1

azureFoundry/azureml-cohere/Cohere-embed-v3-multilingual@1

Cohere Embed Multilingual is the market's leading text representation model used for semantic search, retrieval-augmented generation (RAG), classification, and clustering.

Context window
512
Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Cohere Embed V5 Fast · azureml-cohere v1

azureFoundry/azureml-cohere/Cohere-Embed-V5-Fast@1

Embed V5 Fast is SOTA on search & retrieval benchmarks,establishing itself as the leader in performance for embedding models.

Context window
128,000
Maximum input
8,192
Maximum output
4,096
Input modalities
text, image
Output modalities
image, text
Capabilities
imageOutput, multimodal, visionInput

Cohere Embed V5 Pro · azureml-cohere v1

azureFoundry/azureml-cohere/Cohere-Embed-V5-Pro@1

Embed V5 Pro is SOTA on search & retrieval benchmarks,establishing itself as the leader in performance for embedding models.

Context window
128,000
Maximum input
8,192
Maximum output
4,096
Input modalities
text, image
Output modalities
image, text
Capabilities
imageOutput, multimodal, visionInput

Cohere Parse V5 · azureml-cohere v1

azureFoundry/azureml-cohere/Cohere-parse-v5@1

Cohere Parse 5 is a high-performance document vision parser.

Context window
8,192
Maximum input
8,192
Maximum output
64,000
Input modalities
image
Output modalities
text
Capabilities
visionInput

Cohere Rerank 3.5

vercelAIGatewayCatalog/cohere/rerank-v3.5

A model that allows for re-ranking English Language documents and semi-structured data (JSON).

Context window
4,096
Maximum output
4,096
Input modalities
text
Output modalities
text
Capabilities
reranking

Cohere: Rerank 4 Fast

cohere/rerank-4-fast

Cohere's AI search foundation model for enhancing the relevance of information surfaced within search and RAG systems. Features a 32K context window, multilingual support across 100+ languages, no data pre-processing required, and high performance with lowest latency.

Context window
32,768
Input modalities
text
Output modalities
rerank
Capabilities
rerank

Cohere: Rerank 4 Pro

cohere/rerank-4-pro

Cohere's AI search foundation model for enhancing the relevance of information surfaced within search and RAG systems. Features a 32K context window, multilingual support across 100+ languages, no data pre-processing required, and state of the art performance with low latency.

Context window
32,768
Input modalities
text
Output modalities
rerank
Capabilities
rerank

Cohere: Rerank 5 Fast

cohere/rerank-5-fast-20261028

Rerank 5 Fast is the low-latency tier of Cohere's Rerank 5 family of reranking models. It scores and reorders candidate documents against a query and is suited for high-throughput retrieval such as high-volume search, agent tool loops, and first-pass filtering before a more expen

Context window
32,768
Input modalities
text
Output modalities
rerank
Capabilities
rerank

Cohere: Rerank 5 Pro

cohere/rerank-5-pro-20261028

Rerank 5 Pro is the higher-accuracy tier of Cohere's Rerank 5 family of reranking models. It scores and reorders candidate documents against a query and is suited for retrieval pipelines where ranking quality matters most: complex or reasoning-heavy queries, long or domain-specif

Context window
32,768
Input modalities
text
Output modalities
rerank
Capabilities
rerank

Cohere: Rerank v3.5

cohere/rerank-v3.5

Rerank v3.5 is designed to reorder search results for improved relevance. It supports multi-aspect and semi-structured data reranking over 100+ languages. Ideal for refining results from semantic or keyword search pipelines.

Context window
4,096
Input modalities
text
Output modalities
rerank
Capabilities
rerank

Cohere-rerank-v3.5 · azureml-cohere v1

azureFoundry/azureml-cohere/Cohere-rerank-v3.5@1

Cohere’s Rerank 3.5 provides a significant boost to the relevancy of search results. This AI model, also known as a cross-encoder, precisely sorts lists of documents according to their semantic similarity to a provided query. This allows information retrieval systems to go beyond

Context window
4,096
Maximum output
2,048
Input modalities
text
Output modalities
text

Cohere-rerank-v3.5 · azureml-cohere v2

azureFoundry/azureml-cohere/Cohere-rerank-v3.5@2

Cohere’s Rerank 3.5 provides a significant boost to the relevancy of search results. This AI model, also known as a cross-encoder, precisely sorts lists of documents according to their semantic similarity to a provided query. This allows information retrieval systems to go beyond

Context window
4,096
Maximum output
2,048
Input modalities
text
Output modalities
text

Cohere Rerank v4.0 Fast · azureml-cohere v1

azureFoundry/azureml-cohere/Cohere-rerank-v4.0-fast@1

Rerank improves search systems by sorting documents based on their semantic similarity to a query

Context window
4,096
Maximum output
2,048
Input modalities
text, image
Output modalities
text, image
Capabilities
imageOutput, multimodal, visionInput

Cohere Rerank v4.0 Pro · azureml-cohere v1

azureFoundry/azureml-cohere/Cohere-rerank-v4.0-pro@1

Rerank improves search systems by sorting documents based on their semantic similarity to a query

Context window
4,096
Maximum output
2,048
Input modalities
text, image
Output modalities
text, image
Capabilities
imageOutput, multimodal, visionInput

Cohere Rerank V5 Fast · azureml-cohere v1

azureFoundry/azureml-cohere/Cohere-rerank-v5-fast@1

Rerank V5 improves search systems by sorting documents based on their semantic similarity to a query

Context window
4,096
Maximum input
8,192
Maximum output
2,048
Input modalities
text, image
Output modalities
text, image
Capabilities
imageOutput, multimodal, visionInput

Cohere Rerank V5 Pro · azureml-cohere v1

azureFoundry/azureml-cohere/Cohere-rerank-v5-pro@1

Rerank V5 improves search systems by sorting documents based on their semantic similarity to a query

Context window
4,096
Maximum input
8,192
Maximum output
2,048
Input modalities
text, image
Output modalities
text, image
Capabilities
imageOutput, multimodal, visionInput

command-a

cheaperInference/command-a

Context window
256,000
Maximum output
8,000
Input modalities
text
Output modalities
text
Capabilities
structuredOutputs, toolCalling

Inference prices

Command A

vercelAIGatewayCatalog/cohere/command-a

Command A is Cohere's most performant model to date, excelling at tool use, agents, retrieval augmented generation (RAG), and multilingual use cases. Command A has a context length of 256K, only requires two GPUs to run, and has 150% higher throughput compared to Command R+ 08-20

Context window
256,000
Maximum output
8,000
Input modalities
text
Output modalities
text
Capabilities
structuredOutputs, toolCalling

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