Request to Increase API Rate Limits. Ticket [#3474]

[dawn wadi]

Hello OpenRouter Support Team,

My name is Max, and I am using your API within an n8n workflow. I am currently facing issues with rate limits that result in errors and interruptions of my workflows.

Here are the details:
Each workflow run generates around 15 API requests within a single minute.
Additionally, there is an asynchronous mode where users can upload tables — up to 50 tables at once, which results in ~750 API requests per minute.

With the current limits, this volume leads to rate limit (429) errors, negatively impacting stability and user experience.

I would kindly like to ask you to consider increasing the rate limits for my account to better support this workload.

To give you some context: our organization has about 5,000 employees, and I expect that at least 500 people will be actively using the AI-based solution I am building. This would significantly increase the reliability and adoption of your platform within our company.

Please let me know if you need any additional details, such as logs, usage statistics, or scaling plans.

Thank you very much for your support and consideration!

[coral glacier]

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

Thank you for your detailed request. For increases to API rate limits, OpenRouter evaluates requests based on account type and organizational needs. According to the documentation: "You can learn more about how rate limits work for paid accounts in our rate limits documentation" and "Capacity and rate limits: Fail over into our capacity when your limits are hit" OpenRouter FAQ.

For large-scale or enterprise workloads (such as your described volume), OpenRouter recommends reaching out for custom solutions or enterprise arrangements. You can do this by filling out the Enterprise Contact Form, which is the official way to request increased rate limits or discuss enterprise features Enterprise Info.

Please submit your request and business case through that form. If you have further billing or account concerns, email [email protected].

-# This is an automated response powered by Answer HQ. Use !mute to stop the bot from responding.

[vagrant moat]

Can you tell me what model you're using and post the full error that's returned?

[dawn wadi]

This model is for working with text. Sometimes the model does not respond fully

This one is for describing the conditions

[vagrant moat]

Can you post the full, raw error?

[dawn wadi]

{
"errorMessage": "OpenAI: Rate limit reached",
"errorDescription": "Provider returned error",
"errorDetails": {},
"n8nDetails": {
"time": "25.09.2025, 19:38:44",
"n8nVersion": "1.112.5 (Self Hosted)",
"binaryDataMode": "filesystem"
}
}

[vagrant moat]

Can you see the full response from OpenRouter?

[dawn wadi]

I don't seem to fully understand how to view them. I have the entire answer in n8n.

[vagrant moat]

Ah

I don't have enough information to know for sure, but I assume the provider is rate limiting OpenRouter

Try another model

[dawn wadi]

I've heard that it's possible to increase the api request limits in openrouter, and that it's done through support. I believe these are openrouter limits rather than qwen models.