Command A Vision API Pricing
As of October 10, 2026, Command A Vision costs $1.56 per 1M input tokens and $1.56 per 1M output tokens on Oracle Cloud (OCI). It has a 256,000-token context window and returns up to 8,192 tokens per response.
- Input
- $1.56 / 1M tokens
- Output
- $1.56 / 1M tokens
- Context window
- 256,000 tokens
- Max output
- 8,192 tokens
- Providers
- 1
- Added to LiteLLM
- April 2026
Command A Vision pricing by provider
2 listings across 1 provider. 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 |
|---|---|---|---|---|
| Oracle Cloud (OCI) | oci/cohere.command-a-vision | $1.56 | $1.56 | 256K |
| Oracle Cloud (OCI)snapshot 07-2025 | oci/cohere.command-a-vision-07-2025 | $1.56 | $1.56 | 128K |
What Command A Vision costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Oracle Cloud (OCI) | $3.90 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Oracle Cloud (OCI) | $15.91 |
Command A Vision features
- Function calling
- Structured output
- Image input
Use Command A Vision with LiteLLM
Call Command A Vision 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="oci/cohere.command-a-vision",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: command-a-vision
litellm_params:
model: oci/cohere.command-a-vision
# credentials: see the provider's LiteLLM docs pagecurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "command-a-vision",
"messages": [{"role": "user", "content": "Hello!"}]
}'Command A Vision FAQ
How much does Command A Vision cost?
Command A Vision costs $1.56 per 1M input tokens and $1.56 per 1M output tokens on Oracle Cloud (OCI).
What is the context window of Command A Vision?
Command A Vision has a 256,000-token context window and returns up to 8,192 tokens per response.
Which providers offer Command A Vision?
Command A Vision is available from Oracle Cloud (OCI) through LiteLLM, using the model name oci/cohere.command-a-vision.
How do I call Command A Vision with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="oci/cohere.command-a-vision", 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 Vision support?
Command A Vision supports function calling and image input. It does not support structured output.
When did LiteLLM add Command A Vision?
Command A Vision was added to LiteLLM's model price file in April 2026.
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:
- www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/
- www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing
LiteLLM docs: Oracle Cloud (OCI).
Provider pages: Oracle Cloud (OCI).
