#Does OpenRouter have Token Per Minute (TPM) and Request per minute (RPM) limits?

1 messages · Page 1 of 1 (latest)

fathom fulcrum
#

The api key of OpenAI has tiers on which depending on which tier you are you have TPM and RPM. Does Open Router have some limits? Is yes which RPM and TPM we have when using OpenAI models via open router or any other models?

Documentation of Open AI: https://platform.openai.com/docs/models/gpt-4.1

Thanks!

elder rampartBOT
#

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

I don't have specific documentation for exact Token Per Minute (TPM) or Request Per Minute (RPM) limits for OpenRouter API keys or for usage of OpenAI models via OpenRouter. The OpenRouter documentation and model pages do not mention per-key or per-model TPM/RPM limits like OpenAI does. Error messages such as "429 - Too many requests!" can occur, but no precise thresholds are documented.

For confirmed and up-to-date limits, please verify with the mods or check the OpenRouter docs directly. You can also review details and error handling on the Provider Routing Docs or individual Model pages, but specific RPM/TPM values are not listed there.

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

OpenRouter
OpenRouter

A router for LLMs and other AI models

OpenRouter Documentation
OpenRouter Quickstart Guide

Get started with OpenRouter's unified API for hundreds of AI models. Learn how to integrate using OpenAI SDK, direct API calls, or third-party frameworks.

OpenRouter Documentation
Provider Routing - Smart Multi-Provider Request Management

Route AI model requests across multiple providers intelligently. Learn how to optimize for cost, performance, and reliability with OpenRouter's provider routing.

OpenRouter
OpenRouter

A router for LLMs and other AI models

fathom fulcrum
#

Can anyone help please? AI did not respond.

Thanks!

elder rampartBOT
#

I don't have specific documentation for Token Per Minute (TPM) or Request Per Minute (RPM) limits for OpenRouter API keys or models, including when using OpenAI models via OpenRouter. These limits are not mentioned on the official documentation or status pages. For exact and current limits, please verify with the mods or check the OpenRouter docs directly. You can also review the OpenRouter Status page for any known issues, but it does not list usage quotas.

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

OpenRouter Documentation
OpenRouter Quickstart Guide

Get started with OpenRouter's unified API for hundreds of AI models. Learn how to integrate using OpenAI SDK, direct API calls, or third-party frameworks.

OpenRouter
OpenRouter Status

OpenRouter Incident History

torn belfry
#

Hello, My account is OpenAI Tier 1, which has a TPM (Tokens Per Minute) limit of only 30,000. When I send more than 30K token its being rejected because it's larger than my entire per-minute quota. And I receive a 200 OK error it appears to be how OpenRouter's proxy handles this specific rejection from OpenAI. So I think in a sense Openrouter have TPM limits that are set by the provider

fathom fulcrum
#

!mute

elder rampartBOT
#

🔇 Thread muted. The bot will no longer respond here.

fathom fulcrum
#

Where can you see which OpenAI tier you have? Is there any way to set up an account with bigger TPM?

torn belfry
#

to setup an account with bigger TPM you need to charge your accoutn

fathom fulcrum
#

Yeah that's clear, I am concerned about the TPM and RPM that OpenRouter has using their API keys, not mine.

torn belfry
#

isn't it that openrouter require BYOK for openai? doesn't that mean your tier of openai reflect it

fathom fulcrum
#

AFAIK you can use yours or theirs.

torn belfry
#

its not possible to use their key

gaunt slate
#

You can't use their key through the API though