OpenRouter Errors

If you're encountering errors while using OpenRouter models on JanitorAI, this guide covers common error messages, their causes, and how to resolve them step-by-step.

General Connection Error

Error Message:

“A network error occurred, you may be rate limited or having connection issues: NetworkError when attempting to fetch resource (unk)”

Fix:

• Refresh the JanitorAI page after setting up your proxy.
• Ensure your API URL is correct (watch for double slashes or repeated /chat/completions).

Correct API URL:

https://openrouter.ai/api/v1/chat/completions

PROXY ERROR 400: Invalid Model ID

Message:

{"error":{"message":"is not a valid model ID","code":400}}

Cause: Invalid or misspelled model name.

Fix: Use one of the valid model names below:

Correct Model Names:

• R1 Free: deepseek/deepseek-r1:free
• R1 Paid: deepseek/deepseek-r1
• V3 Free: deepseek/deepseek-chat-v3-0324:free
• V3 Paid: deepseek/deepseek-chat-v3-0324
• Legacy V3 Free: deepseek/deepseek-chat:free

PROXY ERROR 401: No Auth Credentials Found

Message:

{"error":{"message":"No auth credentials found","code":401}}

Cause: Problem with your API key.

Fix:

• Generate a new API key from OpenRouter.
• Avoid copying extra spaces.
• Rarely: This error occurs if you create a key on one device but use it on another.
• Whitelist janitorai.com and openrouter.ai in any extensions like AdGuard.
• Enable “Model Training” in your OpenRouter Privacy Settings for free DeepSeek models.

PROXY ERROR 404: No Endpoints Found

Message:

{"error":{"message":"No endpoints found matching your data policy."}}

Fix: Enable Model Training in OpenRouter Privacy Settings.

Proxy Error 408

Message:

 {"error":{"message":"timeout","code:408}} (unk}

Fix: OpenRouter is currently down. There is no fix other than to wait it out.

PROXY ERROR 402: Insufficient Credits

Message:

“Your account or API Key has insufficient credits.”

Fix:

• Add more credits to your OpenRouter account.
• Or switch to a free version of the model.

PROXY ERROR 405: Bad API URL

Cause: The API URL is malformed (e.g., extra slashes or characters).

Fix: Use this exact URL:

https://openrouter.ai/api/v1/chat/completions

Rate Limit Errors

Error Message Variants:

• Rate limit exceeded: free-models-per-day
• PROXY ERROR: Unknown response: [object Object]

Daily Limits:

• 50 messages/day on free models if you have less than $10 in credits.
• 1000 messages/day if you have $10 or more in credits.

Other Limits:

• 10 messages per minute — resets every 3 hours.
• Daily limit resets at 12AM GMT.

Just wait for the limits to reset.

Provider Returned Error / No Response from Bot

Possible Causes:

• R1 model: Token limits exceeded due to reasoning bloating the response.
• Server overload or downtime.
• You're rerolling too fast.
• Triggered filter on models like Gemini 2.5.

Advanced Troubleshooting Steps

Step 1: Ignore Taragon Provider

1. Go to: OpenRouter > Settings > Ignored Providers.
2. Select Taragon.
3. Click Save.
4. Refresh Janitor.

If fixed: ✅ Done.

If not: proceed to Step 2.

Step 2: Ask for Model Info

Some models (e.g., Gemini 2.5) have filters that can trigger errors.

Step 2.5: Have the user generate a new API key and try again.

If fixed: ✅ Done.

If not: proceed to Step 3.

Step 3: Use DevTools Fix (PC Only)

🔗 Our DevTools Guide

Unknown Worker Error

Message:

“Unknown prompt response from worker for OpenAI proxy generation”

Fix: Refresh JanitorAI — this is usually caused by a momentary queue or proxy hiccup.

Updated on: 03/08/2025