Mintplex-Labs/anything-llm · error · Error

Invalid response body returned from OpenRouter

Error message

Invalid response body returned from OpenRouter: ${result.output?.error?.message || "Unknown error"} ${result.output?.error?.code || "Unknown code"}

What it means

Response-shape guard in OpenRouterLLM.getChatCompletion: the call resolved but the payload has no non-empty choices array, so OpenRouter returned an error body or malformed response; the embedded error message and code are surfaced for diagnosis.

Solutions

1. Check the OpenRouter error message and code in the response.
2. Verify the model id and credits/quota on OpenRouter.
3. Retry with a valid model.

When it happens

Trigger: Thrown when OpenRouter returns an error body.

Common situations: Invalid model, insufficient credits, or provider error.

AI-assisted analysis of Mintplex-Labs/anything-llm@f92433b4ea (2026-08-18). Data as JSON: /api/errors/5ad39777a0959d6a. Report an issue: GitHub.

Appendix: source

Thrown at server/utils/AiProviders/openRouter/index.js:280

          model: this.model,
          messages,
          temperature,
          // This is an OpenRouter specific option that allows us to get the reasoning text
          // before the token text.
          include_reasoning: true,
          ...serviceTierParam(this.serviceTier, this.log.bind(this)),
          user: user?.id ? `user_${user.id}` : "",
        })
        .catch((e) => {
          throw new Error(e.message);
        })
    );

    if (
      !result?.output?.hasOwnProperty("choices") ||
      result?.output?.choices?.length === 0
    )
      throw new Error(
        `Invalid response body returned from OpenRouter: ${result.output?.error?.message || "Unknown error"} ${result.output?.error?.code || "Unknown code"}`
      );

    return {
      textResponse: this.#parseReasoningFromResponse(result.output.choices[0]),
      metrics: {
        prompt_tokens: result.output.usage.prompt_tokens || 0,
        completion_tokens: result.output.usage.completion_tokens || 0,
        total_tokens: result.output.usage.total_tokens || 0,
        outputTps: result.output.usage.completion_tokens / result.duration,
        duration: result.duration,
        model: this.model,
        provider: this.className,
        timestamp: new Date(),
      },
    };
  }

View on GitHub (pinned to f92433b4ea)