ModelsCommand

Cohere's Command A Reasoning Model

Capabilities
ReasoningMultilingualSafety ModesCitationsTool UseStructured OutputsImage Inputs
Pricing

For both trial keys and production keys, Command A Reasoning is free until rate limits are reached. Learn more about rate limits for different models and key types here.

Command A Reasoning can be used in production through Cohere's Model Vault.

Specifications
    Context Window: 256,000 tokens
    Max Output Tokens: 32,000 tokens
    Knowledge Cutoff: June 1, 2024
API Endpoints

Model ID

command-a-reasoning-08-2025

Chat V2Chat CompletionsChat V1

Description

Command A Reasoning is Cohere’s first reasoning model to date, excelling at real world enterprise tasks including tool use, retrieval augmented generation (RAG), agents, and multilingual use cases. At 111B parameters, Command A has a context length of 256K. Command-a-Reasoning (CAR) is optimized to run on 4x H100 GPUs for production workloads. For non-production tasks such as tryouts and evaluations, it can also run on 4x A100 GPUs.

What Can Command A Reasoning Be Used For?

Command A is excellent for:

  • Agentic Use Cases: Taking autonomous actions and interacting with the environment to solve problems.
  • Tool Use: Able to leverage a variety of tools, such as search engines and APIs.
  • Multilingual: Able to reason over multilingual inputs, providing support to user queries in 23 different languages.

There’s more to be said about token budgets, enabling and disabling the thinking operation, etc., which can be found in our dedicated Reasoning guide.