Command Nightly API Pricing

As of October 10, 2026, Command Nightly costs $1.00 per 1M input tokens and $2.00 per 1M output tokens on Cohere. It has a 4,096-token context window and returns up to 4,096 tokens per response.

By CohereModel ID command-nightlyPrices updated October 10, 2026Checked October 10, 2026

Input: $1.00 / 1M tokens
Output: $2.00 / 1M tokens
Context window: 4,096 tokens
Max output: 4,096 tokens
Providers: 1

Command Nightly pricing by provider

1 listing 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
Cohere	`command-nightly`	$1.00	$2.00	4K

What Command Nightly costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Cohere

$3.00

Use Command Nightly with LiteLLM

Call Command Nightly through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK

from litellm import completion

response = completion(
    model="command-nightly",
    messages=[{"role": "user", "content": "Hello!"}],
)

Proxy config.yaml

model_list:
  - model_name: command-nightly
    litellm_params:
      model: command-nightly
      api_key: os.environ/COHERE_API_KEY

Call the proxy

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "command-nightly",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Command Nightly FAQ

How much does Command Nightly cost?

Command Nightly costs $1.00 per 1M input tokens and $2.00 per 1M output tokens on Cohere.

What is the context window of Command Nightly?

Command Nightly has a 4,096-token context window and returns up to 4,096 tokens per response.

Which providers offer Command Nightly?

Command Nightly is available from Cohere through LiteLLM, using the model name command-nightly.

How do I call Command Nightly with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="command-nightly", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request.

LiteLLM docs: Cohere.

Provider pages: Cohere.