Cohere
FlagshipNew
Command R+
Cohere's most powerful model, optimized for RAG and tool use
Input
$3
per 1M tokens
Output
$15
per 1M tokens
Context
128K
window
Max output
Not listed
tokens
Open model profile >
Back to providers
Cohere
Cohere leads in providing enterprise AI solutions, specializing in Retrieval-Augmented Generation (RAG) and complex tool use. Their Command R series is optimized for long-context industrial applications.
Models
27
Indexed for this provider.
Region
CA
Country metadata when available.
This page is now route-specific, so provider discovery is indexable and shareable instead of living behind a client-only subview on the homepage.
Cohere
FlagshipNew
Command A Reasoning (082025)
Cohere reasoning-optimized model
Input
$2.5
per 1M tokens
Output
$10
per 1M tokens
Context
289K
window
Max output
Not listed
tokens
Open model profile >
Cohere
FlagshipNew
Command A Vision (072025)
Cohere multimodal model with vision capabilities
Input
$2.5
per 1M tokens
Output
$10
per 1M tokens
Context
128K
window
Max output
Not listed
tokens
Open model profile >
Cohere
FlagshipNew
Command A Translate (082025)
Cohere specialized translation model
Input
$2.5
per 1M tokens
Output
$10
per 1M tokens
Context
9K
window
Max output
Not listed
tokens
Open model profile >
Cohere
Flagship
Command R
High-performance model for long-context tasks and RAG
Input
$0.5
per 1M tokens
Output
$1.5
per 1M tokens
Context
128K
window
Max output
Not listed
tokens
Open model profile >
Cohere
New
Command R7b Arabic (022025)
Compact 7B parameter model for efficient inference
Input
$0.038
per 1M tokens
Output
$0.15
per 1M tokens
Context
128K
window
Max output
Not listed
tokens
Open model profile >
Cohere
New
Rerank v4.0 Fast
Fast reranking model
Input
$0.2
per 1M tokens
Output
Contact
per 1M tokens
Context
32.8K
window
Max output
Not listed
tokens
Open model profile >
Cohere
New
Rerank v4.0 Pro
Professional reranking model
Input
$2
per 1M tokens
Output
Contact
per 1M tokens
Context
32.8K
window
Max output
Not listed
tokens
Open model profile >
Cohere
New
Embed v4.0
Multimodal embedding model
Input
$0.1
per 1M tokens
Output
Contact
per 1M tokens
Context
8.2K
window
Max output
Not listed
tokens
Open model profile >
Cohere
New
Rerank English v3.0
Semantic search reranking model for English
Input
$2
per 1M tokens
Output
Contact
per 1M tokens
Context
4.1K
window
Max output
Not listed
tokens
Open model profile >
Cohere
New
Embed English v3.0
State-of-the-art English text embedding model
Input
$0.1
per 1M tokens
Output
Contact
per 1M tokens
Context
512
window
Max output
Not listed
tokens
Open model profile >
Cohere
New
Embed Multilingual v3.0
High-performance multilingual embedding model supporting 100+ languages
Input
$0.1
per 1M tokens
Output
Contact
per 1M tokens
Context
512
window
Max output
Not listed
tokens
Open model profile >
Cohere
Command R7b (122024)
Compact 7B parameter model for efficient inference
Input
$0.038
per 1M tokens
Output
$0.15
per 1M tokens
Context
132K
window
Max output
Not listed
tokens
Open model profile >
Cohere
C4ai Aya Vision (32)b
Open-source multilingual vision-language model
Input
$0.5
per 1M tokens
Output
$1.5
per 1M tokens
Context
16.4K
window
Max output
Not listed
tokens
Open model profile >
Cohere
C4ai Aya Vision 8b
Open-source multilingual vision-language model
Input
$0.5
per 1M tokens
Output
$1.5
per 1M tokens
Context
16.4K
window
Max output
Not listed
tokens
Open model profile >
Cohere
Command
Instruction-following model for business applications
Input
$1
per 1M tokens
Output
$2
per 1M tokens
Context
4.1K
window
Max output
Not listed
tokens
Open model profile >
Cohere
Rerank Multilingual v3.0
Semantic reranking model
Input
$2
per 1M tokens
Output
Contact
per 1M tokens
Context
4.1K
window
Max output
Not listed
tokens
Open model profile >
Cohere
Rerank v3.5
Semantic reranking model
Input
$2
per 1M tokens
Output
Contact
per 1M tokens
Context
4.1K
window
Max output
Not listed
tokens
Open model profile >
Cohere
Embed English Light v2.0
Lightweight embedding model
Input
$0.1
per 1M tokens
Output
Contact
per 1M tokens
Context
512
window
Max output
Not listed
tokens
Open model profile >
Cohere
Embed English Light v3.0
Lightweight embedding model
Input
$0.1
per 1M tokens
Output
Contact
per 1M tokens
Context
512
window
Max output
Not listed
tokens
Open model profile >
Cohere
Embed English v2.0
Text embedding model
Input
$0.1
per 1M tokens
Output
Contact
per 1M tokens
Context
512
window
Max output
Not listed
tokens
Open model profile >
Cohere
Embed Multilingual Light v3.0
Multilingual embedding model
Input
$0.1
per 1M tokens
Output
Contact
per 1M tokens
Context
512
window
Max output
Not listed
tokens
Open model profile >
Cohere
Embed Multilingual v2.0
Multilingual embedding model
Input
$0.1
per 1M tokens
Output
Contact
per 1M tokens
Context
256
window
Max output
Not listed
tokens
Open model profile >
Cohere
Embed English Light v3.0 Image
Lightweight embedding model
Input
$0.1
per 1M tokens
Output
Contact
per 1M tokens
Context
Not listed
window
Max output
Not listed
tokens
Open model profile >
Cohere
Embed English v3.0 Image
Text embedding model
Input
$0.1
per 1M tokens
Output
Contact
per 1M tokens
Context
Not listed
window
Max output
Not listed
tokens
Open model profile >
Cohere
Embed Multilingual Light v3.0 Image
Multilingual embedding model
Input
$0.1
per 1M tokens
Output
Contact
per 1M tokens
Context
Not listed
window
Max output
Not listed
tokens
Open model profile >
Cohere
Embed Multilingual v3.0 Image
Multilingual embedding model
Input
$0.1
per 1M tokens
Output
Contact
per 1M tokens
Context
Not listed
window
Max output
Not listed
tokens
Open model profile >