Closed SourceCohereReleased 2024-08

Command R+

Cohere's 2024 RAG and tool-use model, still live on the Cohere API but superseded by Command A and Command A+

Cohere has replaced this model with Command A+.

Context window

128K tokens

Input / 1M tokens

$2.50

Output / 1M tokens

$10.00

Provider

Cohere

$2.50 per 1M input tokens and $10.00 per 1M output tokens (Command R+ 08-2024), listed under legacy pricing for existing customers on Cohere's pricing page; OpenRouter charges the same. · Data verified 2026-11-11

Command R+ (08-2024 build) is Cohere's 2024 enterprise model for retrieval-augmented generation (RAG) and multi-step tool use. It has a 128K-token context window and 4K max output, grounds responses in supplied documents with citations, sequences tool calls for agentic workflows, and is optimized for 10 languages. The 08-2024 update delivered roughly 50% higher throughput and 25% lower latency over the prior version. It is still live on the Cohere API, but Cohere lists it under legacy pricing for existing customers and recommends Command A for most use cases. Command A and then Command A+ (May 2026) replaced it as Cohere's flagship. Amazon Bedrock ended Command R+ on August 19, 2026.

Capability index

Relative estimates (0-100) to place this model against its peers, grounded in published benchmarks.

Coding
60
Reasoning
70
Math
58
Multimodal
5
Long context
78
Speed
72
Cost efficiency
60

How to access it

Call the Cohere API (Chat endpoint) with model 'command-r-plus-08-2024' using the official 'cohere' SDK, or use OpenRouter (cohere/command-r-plus-08-2024). Amazon Bedrock ended its Command R+ model on August 19, 2026. Cohere recommends Command A (command-a-03-2025) for most use cases; its newest flagship is Command A+ (command-a-plus-05-2026).

Strengths

  • ✓Retrieval-augmented generation with inline citations
  • ✓Multi-step tool use for agentic workflows
  • ✓128K-token context window
  • ✓Multilingual support optimized for 10 languages
  • ✓Still served on the Cohere API and OpenRouter at $2.50/$10 per 1M tokens

Best for developers who...

Retrieval-augmented generation with citationsMulti-step tool-use / agentsMultilingual enterprise assistantsExisting integrations built on the 08-2024 build

When to choose it (and when not to)

Reach for Command R+ when...

  • →Your core use case is grounded RAG with citations
  • →You already run Command R+ and want to postpone migration
  • →You need reliable multi-step tool/agent orchestration
  • →You need multilingual responses across the 10 optimized languages

Look elsewhere if...

  • ✕You want Cohere's newer models (Command A, or Command A+ from May 2026)
  • ✕You need Amazon Bedrock (Command R+ reached end of life there on August 19, 2026)
  • ✕You need outputs longer than 4K tokens
  • ✕You want multimodal (image/audio) input

How to use it

  • ›Pass source documents through the Chat endpoint's documents field to get grounded, cited answers
  • ›Define clear tool schemas to enable reliable multi-step tool use
  • ›Rely on the model's ability to decline unanswerable questions to reduce hallucination
  • ›For non-English tasks, prompt in one of the 10 optimized languages

Quickstart

Python
import cohere

co = cohere.ClientV2(api_key="YOUR_COHERE_API_KEY")

resp = co.chat(
    model="command-r-plus-08-2024",
    messages=[{"role": "user", "content": "Draft a short product update email."}],
)
print(resp.message.content[0].text)

Requires the official 'cohere' Python SDK (pip install cohere). Amazon Bedrock ended its Command R+ model (cohere.command-r-plus-v1:0) on August 19, 2026, so use the Cohere API or OpenRouter.

API model id: command-r-plus-08-2024

Benchmarks

BenchmarkScoreNotes
RAG (BEIR)Top-5Competitive on standard RAG benchmarks
MMLU~75%Not the primary benchmark focus

Source: Cohere Command R+ documentation

Compare Command R+

Compare Command R+ with any other model

Build a comparison →
All model comparisons →

Learn the concepts