LLM Reference
Cohere API

Cohere API

Researched 10d agoAI LabTier 1

Cohere

CodingRAGAgentsLong contextVisionClassificationJSON / Tool useAIHighlight

Cohere API offers 18 tracked models (5 with output token pricing). This catalog covers coding, rag, and agents; open any model detail page for benchmarks, batch tiers, and migration prompts.

Covers 7 workload areas across 18 tracked models; last verified 2026-09-01.

Use it for

  • Teams comparing token and batch pricing across this provider's models
  • Operators routing coding, rag, and agents workloads through this API

Do not use it for

  • Final benchmark picks without opening the relevant model detail page

Tracked models

18

Models available through this provider

Priced output routes

5

Models with output token pricing tracked

Cheapest output

$0.600

Command Light on this route

Batch-ready models

0

No batch pricing tracked

Latest model release

2026-08-27

15d since newest release

Freshness

2026-09-01

Researched 10d ago

fresh

Routes available via routers & gateways

Browse routers ->

Information

TypeAI Lab
TierTier 1
Models18
CompanyCohere
Founded2019
Toronto, Ontario, Canada

Cohere is a leading enterprise AI company that specializes in developing large language models (LLMs) and Retrieval-Augmented Generation (RAG) capabilities. Their AI platform is designed to solve real-world business challenges with a focus on data security, privacy, and customization. Key features of Cohere's AI platform include: 1. Enterprise-grade frontier AI models with industry-leading multilingual capabilities 2. Cloud-agnostic solutions, allowing companies to use Cohere's AI wherever their data is stored 3. High levels of security and privacy, with on-premises and private cloud deployment options 4. Customizable AI solutions tailored to specific enterprise use cases 5. Natural Language Processing (NLP) and Machine Learning technologies Cohere's platform is particularly well-suited for businesses looking to implement AI solutions while maintaining strict control over their data and ensuring compliance with security regulations. The company's focus on multilingual capabilities also makes it an attractive option for global enterprises operating across different languages and regions.

Where this host wins

  • Coding: 1 tracked model with SWE-bench / HumanEval-style scores.
  • RAG: 3 tracked models with ruler / needle retrieval benchmarks.
  • Agentic: 2 tracked models with BFCL, tau-bench, and SWE-bench tool-use coverage.
  • Long-context: 3 tracked models with context-token or InfiniteBench-class signal.

Getting started

Verify: quotas and regions in the linked vendor documentation.

Platform Overview

Cohere's AI platform is centered around its advanced large language models (LLMs), including families like Command, Rerank, and Embed. These models enable enterprises to develop applications that harness generative AI for text generation, summarization, and semantic search. A standout feature is the platform's Retrieval-Augmented Generation (RAG) capability, which enhances response accuracy by integrating external data sources. This allows businesses to dynamically access relevant information, improving the contextual relevance of generated outputs without model retraining. The platform also supports fine-tuning, enabling organizations to customize models with their proprietary datasets for improved performance in specific use cases.

Available Models(18)

View all →
ModelInput (per 1M)Output (per 1M)Type
Cohere Parse v5.0
Serverless
North Mini Code 1.0
Serverless
Command A+
ServerlessProvisioned
Cohere Embed v4.0
Serverless
Cohere Rerank v4.0 Fast
Serverless
Cohere Rerank v4.0 Pro
Serverless
Cohere Rerank v3.5
Serverless
Command R$0.50$1.50
Serverless
Command R+$2.5$10
Serverless
Aya 23 35B$0.50$1.50
Serverless
View full catalog →

Where else to run this