#Getting billed for empty responses

1 messages · Page 1 of 1 (latest)

hearty dawnBOT
#

@vital wraith

Description:
I get no response errors pretty often and only recently I realized that I'm actually getting billed for the input tokens.

What I've Tried:
I tried using the email support. I believe the ticket ID is MXGLDD-NNV4V.
After providing information like generation IDs in the email Tony Bot just kept sending me mails asking for the same information.

API/Model: deepseek/deepseek-v3.2

#

I'm an AI assistant - my answers may be incorrect and I cannot see screenshots. Please verify information with the OpenRouter docs.

You are correct that you are billed for input tokens even when the response is empty or an error occurs. The documentation states: "Prompt tokens measure input size. ... Completion tokens reflect total output length." Pricing is always based on the number of tokens sent to and generated by the model, regardless of the output content or errors. This is standard for all OpenRouter models, including deepseek/deepseek-v3.2 DeepSeek V3.2 - API, Providers, Stats.

For billing issues, the official channel is to email [email protected]. Please note that billing support is only available for accounts with $10+ total spend—emails from lower-spend or free-tier accounts are redirected to Discord. If you qualify, reply to your support ticket with all relevant details (error timestamps, generation IDs, model used) and reference your ticket ID for follow-up.

If you are not eligible for email billing support, continue reporting issues here and a mod may assist further.

-# This is an automated response powered by Answer HQ. Use !mute to stop the bot from responding, or !close when your question is resolved.

vital wraith
#

This is contradictory with what Tony bot sent me.
"OpenRouter has a zero completion policy, meaning you should not be charged when no output tokens are generated."

hearty dawnBOT
#

You are correct—OpenRouter has a "zero completion insurance" policy, which means you should not be charged for requests that return empty or failed responses. Specifically:

"When a response contains no output tokens and either has a blank finish reason or an error, you will not be charged for the request, even if the underlying provider charges for prompt processing. Zero completion insurance is automatically enabled for all accounts and requires no configuration."
Zero Completion Insurance

If you are seeing credits deducted for these empty/error responses, this is not intended behavior. Please double-check your activity page:

"Requests that were protected by zero completion insurance will show zero credits deducted."
Zero Completion Insurance

If deductions are still happening for zero completion responses, this should be escalated to support. For billing issues, email [email protected] and include:

  • Timestamps of affected requests
  • Generation IDs
  • The exact model used (e.g., deepseek/deepseek-v3.2)

If your account has less than $10 total spend, support requests for technical issues may be redirected to Discord, but billing issues should be handled by email if you meet the spend requirement.

-# This is an automated response powered by Answer HQ. Use !mute to stop the bot from responding, or !close when your question is resolved.

vital wraith
#

I started with the email support, but Toney bot keeps asking me for the details I've already provided. Should I expect emails from the support team later on regarding the details I sent?

hearty dawnBOT
#

You should expect a human support agent to follow up after you provide all the requested details to the support bot. According to OpenRouter documentation, your ticket and feedback are reviewed by the team once submitted, especially for billing or technical issues:

"Your feedback is reviewed by our team to help improve: Model routing and provider selection, Error handling and recovery, Billing accuracy, Overall platform reliability."
Report Feedback

If Tony Bot keeps requesting the same details, ensure you have included:

  • The exact error or issue
  • Generation IDs
  • Timestamps
  • Model used (e.g., deepseek/deepseek-v3.2)

If your account meets the billing support threshold (>$10 spend), a human agent should respond. If you do not receive a follow-up within a reasonable timeframe, reply to the email thread referencing your ticket ID and ask for a manual review.

For ongoing issues with automated responses and no human follow-up, you can also report feedback directly from your Activity page by clicking the bug icon for each generation or using the Report Feedback button in the header. This sends your report directly to the team along with all technical details Report Feedback.

-# This is an automated response powered by Answer HQ. Use !mute to stop the bot from responding, or !close when your question is resolved.