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: Command A+

cohere/command-a-plus-05-2026

Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured outputs (JSON object and JSON schema), optional reasoning, and configurable safet

Context window
192,000
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Benchmarks

  • Artificial Analysis: 6.2

Inference prices

  • Published price : $0.15 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $0.30 / input_tokens_per_million · openRouter ↗
  • Published price : $1.50 / output_tokens_per_million · openRouter ↗

Cohere: North Mini Code (free)

cohere/north-mini-code-20260617

North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized for code generation, agentic software engineering, and terminal tasks, and is trained to generalize

Context window
256,000
Input modalities
text
Output modalities
text
Capabilities
reasoning, toolCalling

Benchmarks

  • Artificial Analysis: 3.4

Inference prices

Cohere: Command A

cohere/command-a-03-2025

Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...

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

Benchmarks

  • Artificial Analysis: 13.1
  • LiveBench: 36.696%
  • LMArena: 1,330.953

Inference prices

Cohere Command A · azureml-cohere v1

azureFoundry/azureml-cohere/cohere-command-a@1

Command A is a highly efficient generative model that excels at agentic and multilingual use cases.

Context window
131,072
Maximum input
131,072
Maximum output
8,182
Input modalities
text
Output modalities
text
Capabilities
toolCalling

Cohere Command A · azureml-cohere v3

azureFoundry/azureml-cohere/cohere-command-a@3

Command A is a highly efficient generative model that excels at agentic and multilingual use cases.

Context window
131,072
Maximum output
4,096
Input modalities
text
Output modalities
text

Cohere Command A · azureml-cohere v4

azureFoundry/azureml-cohere/cohere-command-a@4

Command A is a highly efficient generative model that excels at agentic and multilingual use cases.

Context window
131,072
Maximum output
4,096
Input modalities
text
Output modalities
text

Cohere-command-a-plus-05-2026 · azureml-cohere v1

azureFoundry/azureml-cohere/Cohere-command-a-plus-05-2026@1

Command A is a highly efficient generative model that excels at agentic and multilingual use cases.

Context window
128,000
Maximum input
128,000
Maximum output
64,000
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, reasoning, toolCalling, visionInput

Cohere: Command R (08-2024)

cohere/command-r-08-2024

command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and is competitive with the previous version of the lar

Context window
128,000
Input modalities
text
Output modalities
text
Capabilities
structuredOutputs, toolCalling

Inference prices

Cohere: Command R+ (08-2024)

cohere/command-r-plus-08-2024

command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint the same. Read the launch post [here](https://do

Context window
128,000
Input modalities
text
Output modalities
text
Capabilities
structuredOutputs, toolCalling

Benchmarks

  • LiveBench: 30.351%

Inference prices

Cohere: Command R7B (12-2024)

cohere/command-r7b-12-2024

Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning and multiple steps. Use of this model is subject to Cohere's [Usage Policy](https://docs.cohere.co

Context window
128,000
Input modalities
text
Output modalities
text
Capabilities
structuredOutputs, toolCalling

Inference prices

Cohere Embed 4 · azureml-cohere v1

azureFoundry/azureml-cohere/embed-v-4-0@1

Embed 4 transforms texts and images into numerical vectors

Context window
131,072
Maximum output
4,096
Input modalities
image, text
Output modalities
image, text
Capabilities
imageOutput, multimodal, visionInput

Cohere Embed 4 · azureml-cohere v3

azureFoundry/azureml-cohere/embed-v-4-0@3

Embed 4 transforms texts and images into numerical vectors

Context window
131,072
Maximum output
4,096
Input modalities
image, text
Output modalities
image, text
Capabilities
imageOutput, multimodal, visionInput

Cohere Embed 4 · azureml-cohere v4

azureFoundry/azureml-cohere/embed-v-4-0@4

Embed 4 transforms texts and images into numerical vectors

Context window
131,072
Maximum output
4,096
Input modalities
image, text
Output modalities
image, text
Capabilities
imageOutput, multimodal, visionInput

Cohere Embed 4 · azureml-cohere v5

azureFoundry/azureml-cohere/embed-v-4-0@5

Embed 4 transforms texts and images into numerical vectors

Context window
131,072
Maximum output
4,096
Input modalities
image, text
Output modalities
image, text
Capabilities
imageOutput, multimodal, visionInput

Cohere Embed 4 · azureml-cohere v6

azureFoundry/azureml-cohere/embed-v-4-0@6

Embed 4 transforms texts and images into numerical vectors

Context window
131,072
Maximum output
4,096
Input modalities
image, text
Output modalities
image, text
Capabilities
imageOutput, multimodal, visionInput

Cohere: Embed 5 Fast

cohere/embed-5-fast-20261029

Embed 5 Fast is the lower-latency, cost-efficient tier of Cohere's Embed 5 family of multimodal embedding models (about 1B parameters). It embeds text, images, and interleaved text and image content into a single vector space and is suited for high-volume query embedding, agent l

Context window
128,000
Input modalities
text, image
Output modalities
embeddings
Capabilities
embeddings, multimodal, visionInput

Inference prices

Cohere: Embed 5 Pro

cohere/embed-5-pro-20261029

Embed 5 Pro is the higher-accuracy tier of Cohere's Embed 5 family of multimodal embedding models (about 2.4B parameters). It embeds text, images, and interleaved text and image content into a single vector space and is suited for retrieval and RAG over long or domain-specific do

Context window
128,000
Input modalities
text, image
Output modalities
embeddings
Capabilities
embeddings, multimodal, visionInput

Inference prices

Cohere Embed v3 English · azureml-cohere v1

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

Cohere Embed English 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

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