Question 1

What is Command A Reasoning?

Accepted Answer

Command A Reasoning is a model from Cohere, released on Aug 21, 2025. Command A Reasoning 08 is a Cohere model for enterprise language, retrieval, multilingual, or embedding workloads.

Question 2

How much does Command A Reasoning cost?

Accepted Answer

On the Respan gateway, input starts at $2.50 per 1M tokens on Cohere, and output starts at $10.00 per 1M tokens on Cohere, after gateway discounts.

Question 3

Which providers serve Command A Reasoning on Respan?

Accepted Answer

Command A Reasoning is served by Cohere. Cohere requires your own provider API key (BYOK).

Question 4

What is Command A Reasoning's context window?

Accepted Answer

Command A Reasoning accepts up to 289K tokens of context.

Question 5

How do I use Command A Reasoning with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "cohere/command-a-reasoning-08-2025". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Command A Reasoning?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was Cohere at 97 tokens per second, and the lowest response latency was 2.2 seconds on Cohere. Speed varies with request size and provider.

Question 7

How does Command A Reasoning score on benchmarks?

Accepted Answer

Command A Reasoning has 5 published benchmark scores, including SciCode 30%, Tau2-bench Telecom 37%, and AIME 2025 57%. Each score links to where it was published; the data is collected by llmmetric.com.

Command A Reasoning

Providers

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Certified where it counts.

Benchmarks

Coding2

Agents1

Math1

Knowledge1

Apps