Mintplex-Labs/anything-llm · error

Mistral chat: is not valid for chat completion!

Error message

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

What it means

Guard at the top of MistralLLM.getChatCompletion(): it awaits isValidChatCompletionModel(this.model) and throws if the check fails. The current implementation of isValidChatCompletionModel unconditionally returns true, so this error is effectively dead code unless a subclass overrides the validator or a modified provider version is deployed.

Solutions

  1. Confirm the model id exists: curl -H 'Authorization: Bearer $MISTRAL_API_KEY' https://api.mistral.ai/v1/models
  2. Set MISTRAL_MODEL_PREF to a current id (e.g. mistral-small-latest) or re-select in the UI
  3. Audit any isValidChatCompletionModel override in your codebase
  4. git diff server/utils/AiProviders/mistral/index.js to rule out local modifications

Example fix

# before
MISTRAL_MODEL_PREF=mistral-tiny
# after
MISTRAL_MODEL_PREF=mistral-small-latest
Defensive patterns

Strategy: try-catch

Validate before calling

const valid = await llm.isValidChatCompletionModel(llm.model);
if (!valid)
  throw new Error(`Model ${llm.model} is not available on Mistral`);

Try / catch

try {
  await llm.getChatCompletion(messages);
} catch (e) {
  if (/Mistral chat: .* is not valid/.test(e.message)) {
    // verify id via https://api.mistral.ai/v1/models and update MISTRAL_MODEL_PREF
  }
  throw e;
}

Prevention

When it happens

Trigger: Calling getChatCompletion with an overridden isValidChatCompletionModel that returns false for this.model; or a provider variant where the validator really queries the Mistral models endpoint and MISTRAL_MODEL_PREF names a model Mistral no longer serves (e.g. retired 'mistral-tiny').

Common situations: Forks/plugins adding strict model validation; Mistral deprecating a model id that remains in MISTRAL_MODEL_PREF; version skew after upgrading AnythingLLM.

Related errors

AI-assisted analysis of Mintplex-Labs/anything-llm@3aec848f28 (2026-08-18). Data as JSON: /api/errors/8bc617806bfd4e1d. Report an issue: GitHub.

Appendix: 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 3aec848f28)