# User provided API key rate limit exceeded? **URL:** \ **Category:** Help\ **Created:** [September 24, 2024, 2:07pm UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576 "2024-09-24T14:07:08Z")\ **Posts on this page:** 20\ **Page:** 1
**Author:** ![dantengdanteng](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/dantengdanteng/32/6107_2.png) [@dantengdanteng](https://forum.cursor.com/u/dantengdanteng)\ **Post date:** [September 24, 2024, 2:07pm UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576/1 "2024-09-24T14:07:08Z")
![截屏2024-09-24 21.15.42](https://us1.discourse-cdn.com/cursor1/original/2X/d/de1ef3191d55c06b5b86737c79f1cdd53f7e67e1.png) What can I do with this? Thanks. ---
**Author:** ![deanrie](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/deanrie/32/1263_2.png) [@deanrie](https://forum.cursor.com/u/deanrie)\ **Post date:** [September 24, 2024, 5:23pm UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576/2 "2024-09-24T17:23:38Z")
Hi @dantengdanteng Maybe your balance is out? ---
**Author:** ![dstubblefield](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/dstubblefield/32/8002_2.png) [@dstubblefield](https://forum.cursor.com/u/dstubblefield)\ **Post date:** [October 10, 2024, 3:59pm UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576/3 "2024-10-10T15:59:36Z")
“User Provided API Key Rate Limit Exceeded” Again, this is bullshit! ---
**Author:** ![chysy](https://avatars.discourse-cdn.com/v4/letter/c/43a26b/32.png) [@chysy](https://forum.cursor.com/u/chysy)\ **Post date:** [October 27, 2024, 8:56pm UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576/4 "2024-10-27T20:56:43Z")
I’m also having this problem. AFAICT I’m not exceeding any limit that Claude or OpenAI enforces against my API key. So why is Cursor enforcing a rate limit on API requests that I’m paying for directly? And no, it’s not about the balance, because waiting about 60 sec seems to fix the issue, but slows me down – undermining the whole reason I’m using this API key in the first place rather than waiting for the slow request queue. ---
**Author:** ![TheRealM4rtin](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/therealm4rtin/32/14593_2.png) [@TheRealM4rtin](https://forum.cursor.com/u/TheRealM4rtin)\ **Post date:** [December 4, 2024, 11:46pm UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576/5 "2024-12-04T23:46:14Z")
I also having this problem, i reached the limit on premium models and try to go back using my Anthropic API Key but “User API Key Rate limit exceeded”. If i wait some minutes I can have the model running but not a complete answer. ---
**Author:** ![adarkazanli](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/adarkazanli/32/18136_2.png) [@adarkazanli](https://forum.cursor.com/u/adarkazanli)\ **Post date:** [January 2, 2025, 4:23am UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576/6 "2025-01-02T04:23:36Z")
Anybody has answer to this? I have provided TWO APIs one for Open AI and one for Anthropic but still having the same problem. Waiting does not make much of a difference. Yes, I still have balances and I even have auto-recharge turned on so they can just keep charging when my balance drops below a certain $ amount. Any ideas? ---
**Author:** ![gdforj](https://avatars.discourse-cdn.com/v4/letter/g/9e8a1a/32.png) [@gdforj](https://forum.cursor.com/u/gdforj)\ **Post date:** [January 9, 2025, 11:33am UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576/7 "2025-01-09T11:33:35Z")
Composer should at least have a backoff/retry mechanism. ---
**Author:** ![sapph1re](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/sapph1re/32/19685_2.png) [@sapph1re](https://forum.cursor.com/u/sapph1re)\ **Post date:** [January 12, 2025, 5:40am UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576/8 "2025-01-12T05:40:01Z")
Any solution yet?.. Facing the same issue. So frustrating! Charge me more money, make it slower if needed, but don’t just block the process without even any retry button! ---
**Author:** ![jake](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/jake/32/20459_2.png) [@jake](https://forum.cursor.com/u/jake)\ **Post date:** [January 12, 2025, 10:06am UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576/9 "2025-01-12T10:06:32Z")
Just be aware that Anthropic are having some teething issues with the increased demand on their models over the last month. It’s possible that these limits are being imposed by Anthropic, not by Cursor. To test this, set up a quick Jupyter notebook to test the Anthropic API, e.g. ```python # Install the Anthropic SDK !pip install anthropic # Import the Anthropic client import anthropic # Initialize the Anthropic client with API key client = anthropic.Anthropic( api_key="your_api_key_here" # Replace with your actual API key ) # Send a message to the Claude 3.5 Sonnet model and retrieve a response message = client.messages.create( model="claude-3-5-sonnet-20240620", # Specify the Claude 3.5 Sonnet model max_tokens=1024, # Set the maximum token limit messages=[ {"role": "user", "content": "Write a short sonnet about the ocean."} # Provide the prompt ] ) # Print the response from the Claude 3.5 Sonnet model print(message.content) ``` ---
**Author:** ![danperks](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/danperks/32/19087_2.png) [@danperks](https://forum.cursor.com/u/danperks)\ **Post date:** [January 16, 2025, 10:09am UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576/10 "2025-01-16T10:09:21Z")
I don’t believe we enforce any rate limits on using your API key, so these will be limits enforced on the other end (Anthropic or OpenAI). We have now enabled usage-based pricing for Pro users using premium models, which means if you exceed your 500 fast requests but don’t want to buy another 500, you can enable usage pricing. For Claude 3.5 Sonnet, the cost is $0.04 per request ($20 / 500). ---
**Author:** ![gdforj](https://avatars.discourse-cdn.com/v4/letter/g/9e8a1a/32.png) [@gdforj](https://forum.cursor.com/u/gdforj)\ **Post date:** [February 6, 2025, 6:11am UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576/11 "2025-02-06T06:11:20Z")
Hi @danperks, I understand there can be limitations from 3rd party providers and/or cursor’s API. It makes sense. That being said, this keeps interrupting the composer in agent mode. Since I can’t precisely track and restart it where it was interrupted, I gave to restart the agent from the beginning of the task, very likely to hit the limit again. A very light retry mechanism with exponential back off seems to me like a good way to handle this issue with minimal effort. What do you think? ---
**Author:** ![danperks](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/danperks/32/19087_2.png) [@danperks](https://forum.cursor.com/u/danperks)\ **Post date:** [February 9, 2025, 12:54am UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576/12 "2025-02-09T00:54:51Z")
It’s difficult as what works for Anthropic might be different for OpenAI, and again for any 3rd party APIs that users may use. The best way here would be to use the usage-based pricing feature, and not have to worry about API keys at all! ---
**Author:** ![NeroxTGC](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/neroxtgc/32/44646_2.png) [@NeroxTGC](https://forum.cursor.com/u/NeroxTGC)\ **Post date:** [April 6, 2025, 9:52am UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576/13 "2025-04-06T09:52:23Z")
I started using Anthorpic API in Cursor and hit this error also, I found in [Anthropic Rate Limits Docs](https://docs.anthropic.com/en/api/rate-limits) that: > - You may hit rate limits over shorter time intervals. For instance, a rate of 60 requests per minute (RPM) may be enforced as 1 request per second. Short bursts of requests at a high volume can surpass the rate limit and result in rate limit errors. And the rate limits are in [https://console.anthropic.com/settings/limits](https://console.anthropic.com/settings/limits) So, this is an issue related with Anthropic ;( ---
**Author:** ![iakar](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/iakar/32/46114_2.png) [@iakar](https://forum.cursor.com/u/iakar)\ **Post date:** [April 11, 2025, 1:03am UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576/14 "2025-04-11T01:03:00Z")
I left my desk, went and played racquetball for 2 hours, came back and took a shower and I am still getting the rate error. ---
**Author:** ![bed](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/bed/32/35190_2.png) [@bed](https://forum.cursor.com/u/bed)\ **Post date:** [May 31, 2025, 6:53am UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576/15 "2025-05-31T06:53:37Z")
When registering an OpenAI API Key, the following problems occur. 1. When sending chats twice in a row, a ‘User API Key Rate limit exceeded’ error occurs 2. When searching, a ‘User API Key Rate limit exceeded’ error occurs I can’t use it properly. ![image](https://us1.discourse-cdn.com/cursor1/original/3X/c/7/c7a07e17824f30c5a2d2f98698c593f2b9377ad2.png) ---
**Author:** ![bed](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/bed/32/35190_2.png) [@bed](https://forum.cursor.com/u/bed)\ **Post date:** [June 7, 2025, 7:35am UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576/16 "2025-06-07T07:35:58Z")
I couldn’t solve this problem, so I asked the open ai community about it, but I haven’t heard back for over a week. > **[When I register an API key in cursor ai, I get an error 'User API Key Rate...](https://community.openai.com/t/when-i-register-an-api-key-in-cursor-ai-i-get-an-error-user-api-key-rate-limit-exceeded/1274107?u=bed)** > > When registering an OpenAI API Key, the following problems occur. When sending chats twice in a row, a ‘User API Key Rate limit exceeded’ error occurs When searching, a ‘User API Key Rate limit exceeded’ error occurs I can’t use it properly. ... ---
**Author:** ![albinati](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/albinati/32/28485_2.png) [@albinati](https://forum.cursor.com/u/albinati)\ **Post date:** [July 22, 2025, 11:13am UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576/18 "2025-07-22T11:13:50Z")
If you are using Azure OpenAI you need to increase the TPM Rate Limit. ![image](https://us1.discourse-cdn.com/cursor1/original/3X/d/3/d3698b67a00a8dfa502cd1eb94810628586c8f4a.png) ---
**Author:** ![LARAMediaGroup](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/laramediagroup/32/58850_2.png) [@LARAMediaGroup](https://forum.cursor.com/u/LARAMediaGroup)\ **Post date:** [August 5, 2025, 4:06pm UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576/19 "2025-08-05T16:06:13Z")
We get this a lot, I mean, every 2 lines of code. The “solution” is to type, ‘please continue’ and it works for another 15 seconds. I checked our Open Router credit, that’s not the issue but more like a limitation imposed by Cursor, and the model is cut off. We’re already on a pro yearly package, so it seems like unnecessary or a new way of forcing users to Usage-Based Pricing. Shame, Cursor. ![Screenshot 2025-08-05 at 16.59.59](https://us1.discourse-cdn.com/cursor1/original/3X/1/c/1c74c7b78e62f9f0aef4743edc479e383bda90b6.png) ---
**Author:** ![condor](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/condor/32/73148_2.png) [@condor](https://forum.cursor.com/u/condor)\ **Post date:** [August 10, 2025, 5:48pm UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576/20 "2025-08-10T17:48:25Z")
@LARAMediaGroup do you route external AI API providers through OpenRouter? The error message is shown as received through the API URL you provide. So it may be that the model is rate limited at provider where OpenRouter points to. ---
**Author:** ![bed](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/bed/32/35190_2.png) [@bed](https://forum.cursor.com/u/bed)\ **Post date:** [August 30, 2025, 7:43am UTC](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576/21 "2025-08-30T07:43:53Z")
Windsurf officially offers a model called [Claude 4 BYOK], which allows you to use API keys issued from the Claude console. This works flawlessly. However, Cursor experienced issues with API calls being blocked and slow when using the Claude console API key. [Next page](https://forum.cursor.com/t/user-provided-api-key-rate-limit-exceeded/18576.md?page=2)