How do I send a system prompt from Python?

Put your instructions in a system message first. The Model API also accepts the developer role.

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"]},
)

resp = client.chat.completions.create(
    model="supercosmos-flash",
    messages=[
        {"role": "system", "content": "You are a concise assistant for a bike shop. Answer in two sentences."},
        {"role": "user", "content": "How often should I oil my chain?"},
    ],
)
print(resp.choices[0].message.content)

Every request also includes a short Clatter Labs instruction block, which counts toward input tokens. Your system prompt is added on top of it.

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.
• New accounts get $5 of free credit; top up from $1 to $800 per purchase in Console › Billing › Credits. Billing
• Your key's account is responsible for your end users' text under the Abuse policy. What it means for apps

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.