Command A Reasoning
Command A Reasoning is Cohere's first reasoning model, able to think before generating an output, with tool use for agentic workflows.
Model ID
cohere/command-a-reasoning- Context window
- 289K
- tokens
- Max output
- 33K
- tokens
- Pricing
- Free
- $0 per token, for input and output.
Quickstart
Call Command A Reasoning in one request.
Point the SDK you already use at xKiro and pass the model ID. The same key works for every model in the catalog.
SDK guidesimport osfrom openai import OpenAI client = OpenAI( api_key=os.environ["XKIRO_API_KEY"], base_url="https://api.xkiro.com/v1",) res = client.chat.completions.create( model="", messages=[ {"role": "user", "content": "Explain HTTP caching in two sentences."}, ],) print(res.choices[0].message.content)✓ 200 OK
"model": "cohere/command-a-reasoning"
HTTP caching stores copies of responses so later requests can be served without contacting the origin server. Headers such as Cache-Control and ETag decide how long a copy stays fresh and how it is revalidated.
14 input · 42 output tokens · $0 on this free model
Create an API key in the dashboard and export it as XKIRO_API_KEY.
Pricing
What Command A Reasoning costs.
Free to call on every account, within the daily free-model allowance. No credit card.
Free
$0 per token, for input and output.
Billed fairly
- Requests that fail with a 5xx error are never billed
- Retrying an identical blocking request replays the first result — no double charge
- Cancel a stream and pay only for the tokens generated
Specifications
Limits and capabilities.
- Context window
- 288,768 tokens
- Max output
- 32,768 tokens
- Input
- Text
- Output
- Text
- Provider
- Cohere
- Model ID
- cohere/command-a-reasoning
- Good for
- Long context
Capabilities
- Tool useSupported
- VisionNot supported
- Video inputNot supported
- ReasoningSupported
Reasoning effort
- none
- high
Set it with reasoning_effort in the OpenAI format, or thinking in the Anthropic format.
Supported parameters
- max_tokens
- temperature
- top_p
- stop
- frequency_penalty
- presence_penalty
- seed
- stream
- tools
- response_format
- structured_outputs
- reasoning
- include_reasoning
Compare
Similar models.
Closest in price and context window — same provider first, then alternatives from other providers.
Browse all 69 models| Model | Input / 1M | Output / 1M | ||
|---|---|---|---|---|
| 289K | Free | — | ||
| 288K | Free | — | ||
| 256K | Free | — | ||
| 436K | Free | — | ||
| 262K | Free | — | ||
| 256K | Free | — | ||
| 256K | Free | — | ||
Start building with Command A Reasoning.
Command A Reasoning is free to call. Create a key and start in minutes, no credit card.
No credit card · Cancel anytime · 26 free models, free forever