Back to models
Chat Models

Cohere

Command R+

Best for Research

Dated August 2024 model for grounded answers and multi-step tools; distinct from deprecated Command R+ aliases.

RAGCitations
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-plus-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 generation with references to supplied documents
  • Multi-step tool-use workflows for retrieval and analysis
  • A 128,000-token context and 4,000-token maximum output
  • The dated August 2024 version remains listed as live, distinct from older aliases

Before you choose

  • The live specification widget gives June 1, 2024 as the cutoff, while model prose describes training through February 2023. This guide leaves a single cutoff unverified rather than silently choosing between conflicting descriptions.
  • This is text-only and does not inherit A+ vision or A Reasoning controls.
  • The provider recommends evaluating newer Command A for most uses. Existing workflow results, not age alone, should guide a migration.
  • 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-plus-08-2024 for the model covered here. The website slug is a navigation label, not necessarily the API model ID.
  • Pin command-r-plus-08-2024 instead of the deprecated undated alias; compare behavior before updating a deployed configuration.
  • Keep retrieval, citation validation and tool permissions explicit. A citation marker is not proof that the linked material supports a claim.
  • Use the dated model's published rates; older snapshots, cloud hosts and commercial deployments can differ.

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

Synthesize a grounded research answer

Make every recommendation inspectable.

Synthesize these supplied research excerpts into a recommendation. Cite source IDs for each factual claim, identify disagreement between sources and separate evidence from your judgment. Include a short list of missing facts that could change the recommendation. Do not claim to have searched beyond the material provided.

Workflow 02

Check a multi-step retrieval plan

Require useful evidence at each stage.

Review this question, available retrieval tools and initial search results. Propose the next queries needed to resolve the evidence gaps, explaining what each should establish. Include a stop condition and a check for contradictory sources. Do not execute tools or invent returned documents; this is a plan for an authorized integration.

Workflow 03

Evaluate a dated-model migration

Protect a measured workflow while considering a replacement.

Using these recorded Command R+ outputs, acceptance criteria and candidate replacement outputs, compare factual support, citations, tool choices and omitted requirements. Identify exact regressions and improvements. Recommend additional tests before migration, and do not treat an undated model alias as equivalent to a pinned version.

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$2.50
Output$10.00
  • 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.

Is Command R+ deprecated?

The older command-r-plus alias and April 2024 snapshot were deprecated September 15, 2025. The current model inventory lists command-r-plus-08-2024 as live. Always distinguish the exact API ID from the product name.

Why is the knowledge cutoff unverified?

The live card widget and model prose give different dates. This guide exposes that discrepancy instead of presenting one as uncontested. Use supplied current evidence for time-sensitive questions.

Should I automatically replace it with Command A?

Cohere recommends the newer model for most use cases, but evaluate the actual workflow first. Check citations, tool behavior, output length and cost against a recorded baseline before changing a production configuration.

How does R+ differ from Command R?

Both support grounded text and tool workflows, but R+ has a higher published token rate and is positioned for more demanding tasks. Compare measured outcomes rather than assuming either model is always the right choice.

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.