How do I handle Model API errors in Python?

The OpenAI SDK raises typed exceptions. The Model API's code is in e.body (or e.code).

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"]},
)
import openai

try:
    r = client.chat.completions.create(model="supercosmos-flash", messages=[{"role": "user", "content": "Hi"}])
except openai.RateLimitError as e:          # 429 rate_limited
    print("slow down; retry after", e.response.headers.get("retry-after"))
except openai.AuthenticationError as e:     # 401
    print("check key / X-Clatter-Account:", e.code)
except openai.PermissionDeniedError as e:   # 403 insufficient_scope / account_suspended
    print("forbidden:", e.code, e.body)
except openai.APIStatusError as e:          # 400, 402, 404, 410, 413, 5xx
    print(e.status_code, e.code, e.message)

Stop on 402 out_of_credits, 410 model_retired and any 4xx; retry 429 and 5xx with backoff. See Which errors should I retry?.

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#

• New accounts get $5 of free credit; top up from $1 to $800 per purchase in Console › Billing › Credits. Billing
• Every response has an X-Request-Id; log it so a request can be found later. Why log it
• Each key has its own limit: 10, 30 (default), 60 or 120 requests per minute. Rate limits

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.