Mintplex-Labs/anything-llm · error · RetryError

error.message

Error message

error.message

What it means

OpenRouterProvider.stream() catches failures from the streaming tool-call request to https://openrouter.ai/api/v1 and rethrows OpenAI RateLimitError, InternalServerError, or any APIError as aibitat's RetryError with the original message; AuthenticationError is rethrown raw; other errors pass through. The raw error is console.error'd first, so the console holds the full object. On OpenRouter, 429 can mean your key's limit OR the routed upstream provider's limit, and a 402 (insufficient credits, PaymentRequiredError extends APIError) also lands in this wrap.

Source

Thrown at server/utils/agents/aibitat/providers/openrouter.js:111

    try {
      return await tooledStream(
        this.client,
        this.model,
        messages,
        functions,
        eventHandler,
        { provider: this }
      );
    } catch (error) {
      console.error(error.message, error);
      if (error instanceof OpenAI.AuthenticationError) throw error;
      if (
        error instanceof OpenAI.RateLimitError ||
        error instanceof OpenAI.InternalServerError ||
        error instanceof OpenAI.APIError
      ) {
        throw new RetryError(error.message);
      }
      throw error;
    }
  }

  /**
   * Create a non-streaming completion with tool calling support.
   * Uses native tool calling when enabled via ENV, otherwise falls back to UnTooled.
   */
  async complete(messages, functions = []) {
    const useNative = await this.supportsNativeToolCalling();

    if (!useNative) {
      return await UnTooled.prototype.complete.call(
        this,
        messages,
        functions,
        this.#handleFunctionCallChat.bind(this)

View on GitHub (pinned to 3aec848f28)

Solutions

1. Read the console log for the raw error: 402 -> add credits (retrying never helps), 429 -> check whether it's your key or the upstream model, 404 -> fix the slug
2. Verify OPENROUTER_API_KEY and account credits in the OpenRouter dashboard
3. Confirm the model slug exists at openrouter.ai/models (or fall back to openrouter/auto)
4. For upstream 429s, pin a different provider variant of the same model or wait out the window

Example fix

# before
OPENROUTER_API_KEY=<key>   # account has 0 credits -> 402 -> RetryError every call

# after: top up credits, and pin a valid slug
# agent config: model = "openai/gpt-4o-mini"

// Pre-flight: key valid, credits available, slug listed
const res = await fetch("https://openrouter.ai/api/v1/models", {
  headers: { Authorization: `Bearer ${process.env.OPENROUTER_API_KEY}` },
});
if (!res.ok) throw new Error(`OpenRouter pre-flight failed (${res.status}) — check OPENROUTER_API_KEY`);
// Also check credits: GET https://openrouter.ai/api/v1/credits

const { RetryError } = require("./server/utils/agents/aibitat/error.js");
const isRetryError = (e) => e instanceof RetryError;
const isCreditExhausted = (e) => isRetryError(e) && /402|credit|payment/i.test(String(e.message));

try {
  return await provider.stream(messages, functions, eventHandler);
} catch (error) {
  if (error instanceof OpenAI.AuthenticationError) throw error;
  if (isCreditExhausted(error)) throw new Error("OpenRouter credits exhausted — top up (not retryable)");
  if (error instanceof RetryError && /429|5\d\d/.test(error.message)) return withBackoff(retryStream);
  throw error;
}

When it happens

Trigger: Streaming chat.completions.create with OPENROUTER_API_KEY returning 429 (key rate limit or upstream provider rate limit passed through), 402 when the OpenRouter account is out of credits, 404/400 when this.model (default "openrouter/auto" or a pinned slug) is invalid or has no available upstream, 5xx on routing failures.

Common situations: Trial credit exhausted so every call returns 402 wrapped as RetryError; ':free' model slugs rate-limited per day; pinned model slug removed from the OpenRouter catalog; upstream provider (e.g. a specific vendor) down while openrouter/auto routes into it.

Related errors

• ${error.message}
• error.message
• error.message
• error.message
• error.message

AI-assisted analysis of Mintplex-Labs/anything-llm@3aec848f28 (2026-08-18). Data as JSON: /api/errors/4932d371c4685860. Report an issue: GitHub.