Command A API Pricing
As of October 10, 2026, Command A costs $2.50 per 1M input tokens and $10.00 per 1M output tokens on Cohere. Across 3 providers on LiteLLM, the input price ranges from $1.56 to $2.50. It has a 256,000-token context window and returns up to 8,000 tokens per response.
- Input
- $2.50 / 1M tokens
- Output
- $10.00 / 1M tokens
- Context window
- 256,000 tokens
- Max output
- 8,000 tokens
- Providers
- 3
- Added to LiteLLM
- April 2025
Command A pricing by provider
3 listings across 3 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Context |
|---|---|---|---|---|
| Coheresnapshot 03-2025 | command-a-03-2025 | $2.50 | $10.00 | 256K |
| Oracle Cloud (OCI)snapshot 03-2025 | oci/cohere.command-a-03-2025 | $1.56 | $1.56 | 256K |
| Vercel AI Gateway | vercel_ai_gateway/cohere/command-a | $2.50 | $10.00 | 256K |
What Command A costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Cohere | $10.00 |
| Oracle Cloud (OCI) | $3.90 |
| Vercel AI Gateway | $10.00 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Cohere | $27.00 |
| Oracle Cloud (OCI) | $15.91 |
| Vercel AI Gateway | $27.00 |
Command A features
- Function calling
- Structured output
Use Command A with LiteLLM
Call Command A through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="command-a-03-2025",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: command-a
litellm_params:
model: command-a-03-2025
api_key: os.environ/COHERE_API_KEYcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "command-a",
"messages": [{"role": "user", "content": "Hello!"}]
}'Command A FAQ
How much does Command A cost?
Command A costs $2.50 per 1M input tokens and $10.00 per 1M output tokens on Cohere. Across 3 providers on LiteLLM, the input price ranges from $1.56 to $2.50.
What is the context window of Command A?
Command A has a 256,000-token context window and returns up to 8,000 tokens per response.
Which providers offer Command A?
Command A is available from 3 providers through LiteLLM: Cohere, Oracle Cloud (OCI) and Vercel AI Gateway. The lowest price is on Oracle Cloud (OCI).
How do I call Command A with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="command-a-03-2025", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does Command A support?
Command A supports function calling and structured output.
When did LiteLLM add Command A?
Command A was added to LiteLLM's model price file in April 2025.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
LiteLLM docs: Cohere, Oracle Cloud (OCI), Vercel AI Gateway.
Provider pages: Cohere, Oracle Cloud (OCI), Vercel AI Gateway.
