Question 1

What is Command A?

Accepted Answer

Command A is a model from Cohere, released on Mar 13, 2025. Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary and open-weights models Command A delivers maximum performance with minimum hardware costs, excelling on business-critical agentic and multilingual tasks.

Question 2

How much does Command A cost?

Accepted Answer

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

Question 3

Which providers serve Command A on Respan?

Accepted Answer

2 providers serve Command A: Cohere and OpenRouter. Cohere requires your own provider API key (BYOK).

Question 4

What is Command A's context window?

Accepted Answer

Command A accepts up to 288K tokens of context on its largest provider route.

Question 5

How do I use Command A 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-03-2025". 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?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 36 tokens per second, and the lowest response latency was 0.5 seconds on Cohere. Speed varies with request size and provider.

Question 7

How does Command A score on benchmarks?

Accepted Answer

Command A has 7 published benchmark scores, including RepoQA 92.6%, BFCL Overall 63.8%, and GPQA 50.8%. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output	Capabilities
CohereBYOK only`cohere/command-a-03-2025`	288K	$2.50/M	$10.00/M
OpenRouter`openrouter/cohere/command-a`	256K	$2.50/M	$10.00/M	—

Command A

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Coding2

Agents1

Reasoning1

Knowledge3

Apps

Command A FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.