Back to models
Chat Models

Cohere

Command R

Dated August 2024 text model for cost-conscious grounded answers, citations and tool workflows with 128K context.

RAGTool use
Open AppBrowse All Models

At a glance

Know the model before you prompt.

Cohere API specifications
Context window
128,000 tokens
Maximum output
4,000 tokens
Inputs → output
Text → Text
Knowledge cutoff
Not verified

API model ID: command-r-08-2024

Capabilities & boundaries

What it supports. Where the limits are.

Tool support requires the appropriate API integration; a supported tool is not automatically active in every chat.

Supported API features and tools

  • Grounded text answers with citations to supplied evidence
  • Tool-use workflows through an application integration
  • A 128,000-token context and 4,000-token maximum output
  • Optimized performance across ten key languages, with additional pretraining languages documented separately

Before you choose

  • The Command R card widget gives June 1, 2024 as the cutoff, while the R+ page's shared August 2024 discussion describes both updated models as trained through February 2023. No single uncontested cutoff is asserted here.
  • The model is text-only; do not borrow vision or hybrid-thinking controls from other Command families.
  • Ten optimized languages and additional pretraining languages are different claims, not a promise of equal quality across every language.
  • Context capacity is not a guarantee of complete recall. Keep source IDs, evaluate omissions and verify citations against the underlying documents.
  • A generated plan or tool call does not authorize or execute an external action. Use a configured integration, validate results and keep consequential changes behind human approval.

Reasoning behavior

The reviewed model-specific sources do not establish hybrid thinking controls or an effort-level list for this ID. Do not copy Command A Reasoning's thinking settings into other Command models. State the goal, evidence and answer format, then verify the result.

  • Use command-r-08-2024 for the model covered here. The website slug is a navigation label, not necessarily the API model ID.
  • The new website route is command-r, while the covered API model is command-r-08-2024. Do not send the deprecated bare alias just because it matches the page slug.
  • Supply the documents or authorized retrieval results to ground the answer, then verify that each cited passage supports the corresponding claim.
  • Keep output requests within the 4,000-token ceiling and compare total successful-task cost, including any retries or review.

Put it to work

Start with a more useful prompt.

Original examples from EZ Ai Assist. Adapt these to your task and the features available in your workspace.

Workflow 01

Build a cited answer from a document set

Use a clear rule for missing information.

Answer this customer question using only the supplied documents. Cite document and section IDs for each claim. If the documents do not establish an answer, say so and identify the missing evidence. Keep the response concise and do not turn an example or proposal into an approved policy.

Workflow 02

Validate a proposed tool call

Check arguments and authority before execution.

Review this proposed tool call against the user's request, tool schema and permission rules. Identify missing arguments, unsupported assumptions and any action that needs approval. Suggest a corrected request only when the evidence is sufficient. Do not execute the tool or imply that a record has already been changed.

Workflow 03

Compare grounded-answer costs and quality

Use a common evaluation across model sizes.

Compare these recorded answers from Command R, R7B and R+ using the same evidence and rubric. Score factual support, citation accuracy, omissions and valid formatting. Use only the supplied usage logs and rates to calculate cost. Flag missing data, then recommend what to test next rather than inventing a universal winner.

Developer reference

Cohere API pricing

These are Cohere API reference prices, not EZ Ai Assist subscription prices.

View EZ Ai Assist plans
Standard processing · USD per 1,000,000 tokens
Token typePrice
Input$0.15
Output$0.60
  • Rates come from the named model's current Cohere card. Other hosts, private deployments and commercial agreements can have different terms.
  • Input and output are billed separately. No model-specific cached-input rate is asserted here; absent cache pricing does not mean cached tokens are free.
  • Trial-key limits are separate from production usage. Check current key limits and actual billed usage before scaling a workflow.

Common questions

A few things worth knowing.

Which Command R version is covered?

command-r-08-2024, the dated August 2024 model listed as live. The website's shorter command-r slug is a page address, not a recommendation to use the bare API alias.

What happened to the older Command R alias?

Cohere deprecated command-r and the March 2024 snapshot on September 15, 2025. That notice is separate from the live August 2024 version; check the full ID before making an availability claim.

Why are there two different cutoff dates in the sources?

Command R's current widget lists June 1, 2024. The linked R+ page's discussion of both August 2024 models refers to training through February 2023. The guide marks a single cutoff as unverified and recommends supplying current evidence rather than guessing.

Are all documented languages equally optimized?

No. The page distinguishes ten optimized languages from additional pretraining languages. Test your language pair, terminology and domain with qualified reviewers rather than adding those counts into one quality guarantee.

Can it see current information automatically?

No. Model knowledge and a long context are not a live search service. Provide current evidence or connect an authorized retrieval workflow where supported, and verify the sources before acting on an answer.

How should I test it on my own work?

Use representative examples, explicit pass criteria and difficult counterexamples. Score factual support, omitted requirements and invalid outputs as well as latency and cost. Keep a human escalation path for uncertain or consequential results.

Are these API capabilities included in my EZ Ai Assist plan?

This guide describes the provider API, not subscription entitlements or a promise that every setting is exposed in the app. Check your workspace for model access and supported inputs, and use the EZ Ai Assist pricing page for plan details.

Check the source

Official documentation

Specifications and API prices checked on . Example prompts and workflow advice are editorial guidance from EZ Ai Assist.

Same provider

More from Cohere

Cohere

Command A+

Multimodal Cohere MoE with hybrid reasoning, 48-language support and a 128K context window.

Cohere

Command A

Text-focused Cohere model for grounded answers and tool workflows, with 256K context and 8K output.

Cohere

Command A Reasoning

Hybrid text reasoning with optional thinking budgets, 256K context and 32K output for evidence-heavy workflows.

Cohere

Command A Vision

Text and image understanding for documents, tables and charts, with up to 20 images per request and no tool use.