Mintplex-Labs/anything-llm · error · Error

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

Error message

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

What it means

getChatCompletion validates this.model (default mistral-tiny or MISTRAL_MODEL_PREF) via isValidChatCompletionModel before calling Mistral. Throws with the 'Mistral chat:' prefix when the model id is not recognized as a Mistral chat model.

Source

Thrown at server/utils/AiProviders/mistral/index.js:112

    attachments = [], // This is the specific attachment for only this prompt
  }) {
    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(
        `Mistral 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. Check the model id against Mistral's current model catalog (la plateforme).
2. Refresh the cached model list if AnythingLLM caches Mistral models locally.
3. Set MISTRAL_MODEL_PREF to a valid chat model (e.g. mistral-small-latest).
4. Avoid passing embedding model ids for chat.

Example fix

// before
MISTRAL_MODEL_PREF=mistral-embed  // embedding model, invalid for chat

// after
MISTRAL_MODEL_PREF=mistral-small-latest

const valid = await llm.isValidChatCompletionModel(llm.model);
if (!valid) {
  throw new Error(`Model '${llm.model}' not in Mistral chat catalog — fix MISTRAL_MODEL_PREF.`);
}

function isKnownMistralModel(model, catalog) {
  return typeof model === 'string' && model.length > 0 && catalog.includes(model);
}

try {
  await llm.getChatCompletion(messages, { temperature });
} catch (e) {
  if (/Mistral chat:.*not valid for chat completion/i.test(e.message)) {
    // reconfigure model
  }
}

When it happens

Trigger: getChatCompletion invoked with a this.model not in the resolved Mistral model catalog — typo, an embedding model (e.g. mistral-embed used for chat), or a deprecated model id.

Common situations: MISTRAL_MODEL_PREF set to a retired Mistral model; copy-pasted model id with wrong casing; embedding model used where a chat model is required; stale cached model list.

Related errors

• Minimax chat: ${this.model} is not valid for chat completion
• Novita chat: ${this.model} is not valid for chat completion!
• DeepSeek chat: ${this.model} is not valid for chat completio
• Foundry chat: ${this.model} is not valid or defined model fo
• GroqAI:chatCompletion: ${this.model} is not valid for chat c

AI-assisted analysis of Mintplex-Labs/anything-llm@526360e320 (2026-08-13). Data as JSON: /api/errors/8bc617806bfd4e1d. Report an issue: GitHub.