How do I calculate the cost of a call in Python?

Every response has usage. Multiply by the model's prices per 1M tokens. That's exactly what's billed (rounded up to the next millionth of a dollar).

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.gateway.clatterlabs.xyz/v1",
    api_key=os.environ["CLATTER_API_KEY"],
    default_headers={"X-Clatter-Account": os.environ["CLATTER_ACCOUNT_ID"]},
)

PRICES = {  # USD per 1M tokens (input, output)
    "supercosmos-flash": (1.60, 3.40),
    "supercosmos-max": (1.80, 3.80),
    "supercosmos-heavy": (2.00, 4.40),
}

r = client.chat.completions.create(model="supercosmos-flash", messages=[{"role": "user", "content": "Hi!"}])
p_in, p_out = PRICES[r.model]
u = r.usage
if u.prompt_tokens > 262_000:   # long-context input bills 1.5x
    p_in *= 1.5
cost = u.prompt_tokens * p_in / 1e6 + u.completion_tokens * p_out / 1e6
print(f"${cost:.6f}")

prompt_tokens includes a short Clatter Labs instruction block added to every request. Check prices in GET /v1/models rather than hard-coding them if you want to stay in sync.

The client setup above (base URL, key and the X-Clatter-Account header) is the same in every Python example; see Set up the Python SDK. Full parameter list: Create a chat completion.

Still need help?#

• General support: support@clatterlabs.com or team@clatterlabs.xyz
• Infrastructure questions, or permanent deletion of your data (your whole account or one service): infrastructure@clatterlabs.xyz

We usually reply within the first hour, and always within 24 hours. A full support team is with you.