Command A Reasoning

GA

Cohere's first reasoning model ('thinks' before generating). Context 256k / max output 32k from docs.cohere.com/docs/models.md. Per-token pricing not publicly listed (sales-gated per eesel.ai/pricepertoken 2026 notes) -> null. Knowledge cutoff not published.

Command A Reasoning by Cohere is tracked live in our LLM catalog, with a 256K (256.000-token) context window. It is generally available (GA). Its weights are publicly downloadable, so it can be self-hosted on your own infrastructure.

Last verified: 13 Aug 2026 · sourced from official provider documentation

Provider
Cohere
Status
GA
Input price
Output price
Cached input
Blended price
Context window
256.000 tokens (256K)
Max output
32.000 tokens
Modality
text
Open weights
Yes — self-hostable
Knowledge cutoff
Released
Aug 2025
API string
command-a-reasoning-08-2025

Source: Cohere official documentation ↗

FAQ

Command A Reasoning — questions & answers

What is the context window of Command A Reasoning?

Command A Reasoning has a 256.000-token context window (256K), with up to 32.000 output tokens per request.

Is Command A Reasoning deprecated?

No — Command A Reasoning is generally available (GA) and not currently scheduled for deprecation or retirement in our tracker.

Does Command A Reasoning support image or vision input?

Our catalog lists Command A Reasoning's modalities as text; image/vision input is not among them.

Can I self-host Command A Reasoning?

Yes — Command A Reasoning is an open-weight model: its weights are publicly downloadable, so you can run it on your own infrastructure (subject to its license) instead of only calling Cohere's API.

What is the API model string for Command A Reasoning?

The API model identifier for Command A Reasoning is "command-a-reasoning-08-2025" when calling Cohere's API.