6G
6G-AI
C

Cohere Command R+ / Embed / Rerank

LLM

by Cohere

Cohere specializes in enterprise AI with Command R+ for generation, Embed for embeddings, and Rerank for search optimization. Strong focus on RAG (Retrieval-Augmented Generation) workflows.

Official APIDocumentationFree: Free
API Endpoint

https://dashboard.cohere.com/

Documentation

Official Docs

Pricing

View Pricing

Registration & API Key Steps

1

Step 1

Visit Cohere Dashboard and sign up.

Open link
2

Step 2

Register with email, Google, or GitHub account.

3

Step 3

A Trial API key is automatically created for your account.

4

Step 4

Find your API key in the "API Keys" section of the dashboard sidebar.

5

Step 5

Trial key allows 1,000 calls/month for free (non-production).

6

Step 6

Upgrade to Production key with billing for production use.

Pricing

TierPriceFeatures
Command R+$2.50 / $10.00 per 1M tokensInput / Output. Most capable generative model.
Command R$0.15 / $0.60 per 1M tokensInput / Output. Cost-effective generation.
Embed v4$0.10 per 1M tokensBest-in-class embedding model for search/RAG.
Rerank 3.5$2.00 per 1K searchesRe-rank search results for better relevance.
Trial KeyFree1,000 API calls/month. All models. Non-production use.

Application Tips

Tip 1

Trial key gives 1,000 free API calls/month — generous for experimentation.

Tip 2

Cohere Embed v4 is one of the best embedding models for search and RAG.

Tip 3

Rerank API dramatically improves search relevance — great for RAG pipelines.

Tip 4

Command R is designed specifically for RAG — includes built-in citation generation.

Tip 5

API supports grounded generation with web search connector.

Tip 6

Enterprise deployment available on AWS, GCP, Azure, and private cloud.

China Access Solutions

Access Solution

Requires VPN/proxy for API access from China. No specific China-friendly access method. Consider AWS Bedrock for Cohere models in supported regions.

Code Example

JavaScript / TypeScript
import cohere

co = cohere.ClientV2(api_key="your-api-key")

response = co.chat(
    model="command-r-plus",
    messages=[
        {"role": "user", "content": "Explain RAG in simple terms"}
    ]
)

print(response.message.content[0].text)

# --- Embedding example ---
# embeddings = co.embed(
#     texts=["hello", "world"],
#     model="embed-v4.0",
#     input_type="search_document",
#     embedding_types=["float"]
# )

# --- cURL example ---
# curl https://api.cohere.com/v2/chat \
#   -H "Authorization: Bearer your-api-key" \
#   -H "Content-Type: application/json" \
#   -d '{"model":"command-r-plus","messages":[{"role":"user","content":"Hello!"}]}'

Rate Limits

TierLimits
DefaultTrial: 20 RPM, 1,000 calls/month. Production: 10,000 RPM default. Enterprise: custom limits.

Recommended Use Cases

RAG systemsSemantic searchEnterprise knowledge basesDocument search & retrievalMultilingual applications
Last Updated: 2026-02-10

Related API Guides

O

OpenAI GPT-4o / GPT-4.1 / o3

OpenAI

OpenAI's flagship LLM family including GPT-4o for multimodal tasks, GPT-4.1 for long-context coding, and o3 for advanced reasoning. Industry-leading models with the largest developer ecosystem.

A

Anthropic Claude (Sonnet 4.5 / Opus 4.5)

Anthropic

Anthropic's Claude model family excels in nuanced reasoning, safety, and long-context tasks. Claude Sonnet 4.5 offers the best balance of cost and performance, while Opus 4.5 delivers frontier intelligence.

G

Google Gemini (2.5 Pro / 2.5 Flash)

Google

Google's Gemini models offer a generous free tier, 1M token context window, and strong multimodal capabilities. Gemini 2.5 Pro leads in reasoning, while Flash models provide cost-effective alternatives.

M

Meta Llama 4 (Scout / Maverick)

Meta

Meta's open-source Llama 4 models are free to use and available through multiple cloud providers. Llama 4 Scout and Maverick offer competitive performance at extremely low cost through partner APIs.