How do I handle Model API errors in JavaScript?

The SDK throws OpenAI.APIError subclasses with status, code and headers.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.gateway.clatterlabs.xyz/v1",
  apiKey: process.env.CLATTER_API_KEY,
  defaultHeaders: { "X-Clatter-Account": process.env.CLATTER_ACCOUNT_ID },
});

try {
  await client.chat.completions.create({ model: "supercosmos-flash", messages: [{ role: "user", content: "Hi" }] });
} catch (e) {
  if (e instanceof OpenAI.APIError) {
    console.log(e.status, e.code, e.message, e.headers?.["x-request-id"]);
    if (e.status === 429) console.log("retry after", e.headers?.["retry-after"], "s");
    if (e.status === 402) console.log("out of credits: top up in Console › Billing › Credits");
    if (e.status === 410) console.log("retired model id: switch to a supercosmos id");
  } else throw e;
}

See every code in What does a Model API error look like?.

Every JavaScript example uses the same client (base URL, key and the X-Clatter-Account header); see Set up the JavaScript 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
• Each key has its own limit: 10, 30 (default), 60 or 120 requests per minute. Rate limits
• Every call shows in Console › Logs and Usage as Model API, with its price. See what you spent

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.