429 Too Many Requests. Is it just me or it is not working for now?

[GooksanGom]

Every single try goes to the following result. I understand if it is due to the crowded people wanting to try this new product, but any clue in case it is not?

✕ [API Error: got status: 429 Too Many Requests. {"error":{"message":"{\n  \"error\": {\n    \"code\": 429,\n    \"message\": \"Resource has been
  exhausted (e.g. check quota).\",\n    \"status\": \"RESOURCE_EXHAUSTED\"\n  }\n}\n","code":429,"status":"Too Many Requests"}}]

[Shukolza]

Yes, I an currently facing the same thing.
Maybe it's really overloaded for now, lets just wait

[GooksanGom]

Good to know that I'm not alone with this issue.

Thanks.

[slipstr28]

Started around 23:00 GMT for me, the "too many request" message ( and asking Gemini about it and the allowances) was making me wondering whether i had already used all my daily 1K requests allowance in such a short time performing small action on simple short code).

I've read here and there that the system had "too much" success, thus overloading the planned capacity.

Nevertheless, indication of the actual allowance remaining in /stats would be more than welcome for people only using code assist agent or cli (the usage tracking is today mostly only possible for google cloud develop premium members).

[GooksanGom]

Unfortunately, I installed gemini-cli just 10 minutes before writing this post, and after realizing that the endlessly waiting Google account login was pointless, I tried using a free API key instead — but I was never able to get it to work even once. The error message included in this post is the only result I’ve ever gotten from gemini-cli, and no matter what questions or requests I made, I never received anything else. Despite never receiving a single successful response, I found out through Google AI Studio that some quota was still consumed during these failed attempts. While it’s only a small portion of the total quota (60 per minute, 1k per day), I didn’t like wasting quota on meaningless failures, so I decided to wait until tomorrow.

My current overall assessment of gemini-cli is simply: “epic failure” 👎 for now.

Maybe will get better tomorrow, right?

[slipstr28]

Hmm ... After writing my previous message 1h ago , i managed to get a bit of it for 5min until it started a "psychotic/schizophrenic" loop and hallucination on its code and pulled its plug... I may have just assisted a modern rendition of the scene where HAL9000 gradually loses its memory modules.😵‍💫

I've had planned to evaluate the trial of the "other coding reasoning elephant" contender in the room, time to do that while the capacity issues are taken care, i think.

Let's hope it stabilises, i really like it. 👍