Mintplex-Labs/anything-llm · error

OpenRouter Failed to embed

Error message

OpenRouter Failed to embed: ${error}

What it means

The aggregate wrapper thrown at the end of OpenRouterEmbedder.embedChunks() when one or more batched embedding requests to https://openrouter.ai/api/v1/embeddings failed. Distinct error messages are joined after the prefix and partial data is discarded. The suffix usually carries OpenRouter's own status text: 429 rate limit, 401/402 auth or credit issues, 404 unknown model, or upstream provider errors.

Solutions

  1. Read the suffix — it is OpenRouter's literal error message and determines the fix.
  2. On 402/401: add credit or refresh OPENROUTER_API_KEY.
  3. On 404/model errors: pick a model from OpenRouter's /api/v1/embeddings/models list (e.g. baai/bge-m3).
  4. On 429: slow down ingestion and retry; embedding requests count against the same limits as chat.
Defensive patterns

Strategy: retry

Try / catch

async function embedWithRetry(embedder, chunks, maxAttempts = 4) {
  for (let i = 1; ; i++) {
    try {
      return await embedder.embedChunks(chunks);
    } catch (err) {
      const msg = err.message;
      const transient = msg.includes("429") || msg.includes("Rate limit");
      if (transient && i < maxAttempts) {
        await new Promise((r) => setTimeout(r, i * 10_000));
        continue;
      }
      throw err; // 401/402 (auth/credit) and 404 (model) are not retryable
    }
  }
}

Prevention

When it happens

Trigger: Out of OpenRouter credits (402); 429 when embedding a large document quickly; EMBEDDING_MODEL_PREF set to a model that is not an OpenRouter embedding model (404/no endpoints); the key was revoked; upstream provider outages surfaced through OpenRouter.

Common situations: First big workspace sync on a new OpenRouter account; switching EMBEDDING_MODEL_PREF to a chat model id; free-tier keys hitting RPM limits.

Related errors

AI-assisted analysis of Mintplex-Labs/anything-llm@3aec848f28 (2026-08-18). Data as JSON: /api/errors/11ab5ed75d4432a0. Report an issue: GitHub.

Appendix: source

Thrown at server/utils/EmbeddingEngines/openRouter/index.js:94

        .flat();
      if (errors.length > 0) {
        let uniqueErrors = new Set();
        errors.map((error) =>
          uniqueErrors.add(`[${error.type}]: ${error.message}`)
        );

        return {
          data: [],
          error: Array.from(uniqueErrors).join(", "),
        };
      }
      return {
        data: results.map((res) => res?.data || []).flat(),
        error: null,
      };
    });

    if (!!error) throw new Error(`OpenRouter Failed to embed: ${error}`);
    return data.length > 0 &&
      data.every((embd) => embd.hasOwnProperty("embedding"))
      ? data.map((embd) => embd.embedding)
      : null;
  }
}

async function fetchOpenRouterEmbeddingModels() {
  return await fetch(`https://openrouter.ai/api/v1/embeddings/models`, {
    method: "GET",
    headers: { "Content-Type": "application/json" },
  })
    .then((res) => res.json())
    .then(({ data = [] }) => {
      const models = {};
      data.forEach((model) => {
        models[model.id] = {
          id: model.id,

View on GitHub (pinned to 3aec848f28)