Command R+ (08-2024)
VerifiedCohere's Command R+ excels at RAG, tool use, and long-context reasoning.
About Command R+ (08-2024)
Command R+ employs a transformer-based architecture optimized for retrieval-augmented generation and function calling. Its 128k context window allows it to ingest and reason over lengthy documents without truncation. The August 2024 release includes refinements to multilingual performance and citation accuracy.
Strengths include precise tool orchestration and reduced hallucination when grounded in retrieved sources. As an open-weight model it can be fine-tuned or deployed on private infrastructure. Typical usage covers customer support agents, research assistants, and internal knowledge-base interfaces.
Capabilities
Benchmarks & performance
Independent evaluation scores and measured speed.
Source: Artificial Analysis
How Command R+ (08-2024) compares
Command R+ (08-2024) (striped bar) vs other language models on intelligence, speed and price.
Intelligence
Artificial Analysis Intelligence Index · Higher is better · Command R+ (08-2024) ranks #67 of 67
Price
USD per 1M output tokens · Lower is better · Command R+ (08-2024) ranks #55 of 141
Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Long Document Summarization
The 128k token context enables effective RAG and summarization over extensive reports or research papers while maintaining coherence across sections.
Agentic Tool Integration
Tool use and function calling allow reliable multi-step workflows where the model invokes external APIs or databases based on user instructions.
Multilingual Code Assistance
Strong instruction following combined with code generation supports writing and explaining code in several languages for international development teams.
Strengths & limitations
Strengths
- +Strong enterprise RAG and tool integration
- +Robust multilingual performance
- +Effective long-document handling
Limitations
- –Text-only modality
- –Less emphasis on creative writing
- –Context window capped at 128k tokens
Cost calculator
Estimate what Command R+ (08-2024) would cost for your usage.
Based on Command R+ (08-2024)'s $0.15/1M input · $0.60/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "cohere/command-r-plus-08-2024",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: cohere/command-r-plus-08-2024
Editor's verdict
Command R+ (08-2024) is Cohere's open-weight language models with a 128K-token context window.
On independent testing it scores 7.4 on the Artificial Analysis Intelligence Index.
At $0.60 per 1M output tokens, it is very cost-efficient for its class.
As an open-weight model you can self-host it or call it through a hosted API.
Best suited to strong enterprise rag and tool integration and robust multilingual performance.
Frequently asked questions
The model provides a context window of 128000 tokens.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Other Command models
Sibling versions in the Command family from Cohere.
Similar models
Other language models worth comparing.