Mintplex-Labs/anything-llm · error · Error

CometAPI chat: ${this.model} is not valid for chat completio

Error message

CometAPI chat: ${this.model} is not valid for chat completion!

What it means

Thrown by getChatCompletion when isValidChatCompletionModel returns false. That method syncs the local model cache (storage/models/cometapi/models.json) from the CometAPI /models endpoint, then checks whether this.model is a key in that cached object. If the model id is absent — stale cache, never-synced cache, or an invalid/deprecated model — the chat call is blocked before any API request is made.

Source

Thrown at server/utils/AiProviders/cometapi/index.js:198

    attachments = [],
  }) {
    const prompt = {
      role: "system",
      content: `${systemPrompt}${this.#appendContext(contextTexts)}`,
    };
    return [
      prompt,
      ...formatChatHistory(chatHistory, this.#generateContent),
      {
        role: "user",
        content: this.#generateContent({ userPrompt, attachments }),
      },
    ];
  }

  async getChatCompletion(messages = null, { temperature = 0.7 }) {
    if (!(await this.isValidChatCompletionModel(this.model)))
      throw new Error(
        `CometAPI chat: ${this.model} is not valid for chat completion!`
      );

    const result = await LLMPerformanceMonitor.measureAsyncFunction(
      this.openai.chat.completions
        .create({
          model: this.model,
          messages,
          temperature,
        })
        .catch((e) => {
          throw new Error(e.message);
        })
    );

    if (
      !result.output.hasOwnProperty("choices") ||
      result.output.choices.length === 0

View on GitHub (pinned to 526360e320)

Solutions

1. Call the CometAPI /v1/models endpoint with the API key to confirm the model id is currently listed and matches exactly (including casing).
2. Delete storage/models/cometapi/models.json and the .cached_at file to force a fresh sync, then retry.
3. Update COMETAPI_LLM_MODEL_PREF (or the workspace model selection) to a currently valid CometAPI model id.
4. Verify the storage directory is writable so the model cache can be persisted after sync.

const llm = new CometApiLLM(embedder, modelPref);
const isValid = await llm.isValidChatCompletionModel(llm.model);
if (!isValid)
  throw new Error(`Model "${llm.model}" is not in the CometAPI catalog. Sync the cache or pick a valid id.`);

try {
  return await llm.getChatCompletion(messages, { temperature });
} catch (e) {
  if (/is not valid for chat completion/i.test(e.message)) {
    // force cache refresh and retry once
    fs.unlinkSync(llm.cacheModelPath);
    await llm.isValidChatCompletionModel(llm.model); // triggers resync
    return await llm.getChatCompletion(messages, { temperature });
  }
  throw e;
}

When it happens

Trigger: COMETAPI_LLM_MODEL_PREF is set to a model id that CometAPI no longer lists; the models.json cache file does not exist (first run before sync) or is corrupt; the sync fetch failed silently leaving an empty cache; the model id has trailing whitespace or different casing than the catalog.

Common situations: First-ever CometAPI request on a fresh install where the model cache has not been populated; CometAPI retiring a model and the saved preference still points to it; a typo in the model preference env var; the storage directory is read-only so the cache write fails.

Related errors

• FireworksAI chat: ${this.model} is not valid for chat comple
• ${e.message}
• DeepSeek chat: ${this.model} is not valid for chat completio
• Docker Model Runner chat: ${this.model} is not valid or defi
• Perplexity chat: ${this.model} is not valid for chat complet

AI-assisted analysis of Mintplex-Labs/anything-llm@526360e320 (2026-08-13). Data as JSON: /api/errors/f234e32b7a5b429f. Report an issue: GitHub.