What causes "ApiPie chat: ${this.model} is not valid for chat completion!" in Mintplex-Labs/anything-llm?

Re-fetch the model list in the ApiPie provider settings and pick a currently listed id

ApiPie chat: is not valid for chat completion!

Error message

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

What it means

getChatCompletion first calls isValidChatCompletionModel(this.model), which compares the configured model id against the model list ApiPie returns for your key; a mismatch throws this. ApiPie is an aggregator and model ids are namespaced (e.g. "openrouter/mistral-7b-instruct"), so bare names, typos, retired ids, and keys without upstream access all fail this preflight.

Solutions

Re-fetch the model list in the ApiPie provider settings and pick a currently listed id
Use the fully-qualified namespace/model id exactly as ApiPie lists it
Confirm the key has access to that upstream provider
Clear any stale APIPIE_LLM_MODEL_PREF env override after catalog changes

Example fix

# before
export APIPIE_LLM_MODEL_PREF=mistral-7b-instruct

# after - exact id from ApiPie's /v1/models
export APIPIE_LLM_MODEL_PREF=openrouter/mistral-7b-instruct

Defensive patterns

Strategy: validation

Validate before calling

const models = await apipie.openai.models.list();
const ids = models.data.map((m) => m.id);
if (!ids.includes(modelPref)) {
  return res.status(400).json({ error: `Model ${modelPref} unavailable. Pick one of: ${ids.slice(0, 20).join(", ")}...` });
}

Try / catch

try {
  await apipie.getChatCompletion(messages);
} catch (e) {
  if (/not valid for chat completion/i.test(e.message)) {
    // refresh the model list and repick before retrying once
  }
  throw e;
}

Prevention

Select models from the provider's live list, never free-typed ids
Copy namespaced ids exactly (provider/model)
Re-validate saved preferences after changing API keys

When it happens

Trigger: The default "openrouter/mistral-7b-instruct" removed from ApiPie's catalog; a user-entered APIPIE_LLM_MODEL_PREF without the provider prefix; the key lacking access to the upstream provider; a model id copied from a different provider's docs.

Common situations: Aggregator catalogs churning as upstream models are added or removed; switching keys with different entitlements; stale saved preferences after long idle periods.

Related errors

AI-assisted analysis of Mintplex-Labs/anything-llm@3aec848f28 (2026-08-18). Data as JSON: /api/errors/4b1195d8c4d28516. Report an issue: GitHub.

Appendix: source

Thrown at server/utils/AiProviders/apipie/index.js:192

    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(
        `ApiPie 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 3aec848f28)