How do I limit the length of a reply in Python?

Set max_tokens (or max_completion_tokens). On Max and Heavy it includes reasoning tokens, so leave room for thinking.

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"]},
)

r = client.chat.completions.create(
    model="supercosmos-flash",
    messages=[{"role": "user", "content": "Describe the ocean."}],
    max_tokens=120,
)
print(r.choices[0].message.content)
if r.choices[0].finish_reason == "length":
    print("(cut off by max_tokens)")

Each model has its own cap; GET /v1/models lists max_output_tokens per id (32,768 for Flash and Max, 49,152 for Heavy).

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.

Good to know#

• If calls fail unexpectedly, check status.clatterlabs.com before debugging further.
• Every response has an X-Request-Id; log it so a request can be found later. Why log it
• New accounts get $5 of free credit; top up from $1 to $800 per purchase in Console › Billing › Credits. Billing

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.