Command a Reasoning
Command A Reasoning marked Cohere’s entry into reasoning models, with a hybrid design intended for complex agent tasks. Its enterprise uses include tool use, retrieval augmented generation, and multilingual work. Summary written by AI Index from Cohere’s own pages.
- In Input modalities: Text Out Output modalities: Text
- Reasoning
- Reasoning can be off
- Tool use
- Structured output
Prices
0 offerings · prices as listedNo priced offering is listed for this model yet.
Details
- Knowledge cutoff
- Jun 2024
- Family
- command-a-reasoning
Not stated on Cohere’s pages: max input, reasoning efforts, max thinking budget, built-in tools, aliases.
Cited scores
From third-party leaderboards, not measured by usThis model isn’t on any leaderboard we cite yet.
Changes
All changes →No changes recorded yet.
Sources
- An Overview of Cohere's Models (opens in a new tab) docs.cohere.com · checked Nov 6, 2026
- An Overview of Cohere's Models | Cohere (opens in a new tab) docs.cohere.com · checked Nov 8, 2026
- Announcing Cohere's Command A Reasoning Model | Cohere (opens in a new tab) docs.cohere.com · checked Nov 18, 2026
- Cohere's Command A Reasoning Model | Cohere (opens in a new tab) docs.cohere.com · checked Nov 18, 2026
- models.dev: command-a-reasoning-08-2025 (community data, MIT) (opens in a new tab) github.com · checked Nov 18, 2026
Cohere’s official policies: data use, privacy, terms →
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
Cohere · Canada · cohere.com
Related models
Snapshots, the same family and other models from this provider