I’m an Ultra subscriber paying $200+/month and Antigravity is constantly throttling me. Almost every prompt I send gets hit with rate limit errors and has to retry 3-4 times before I get a response. A simple request that should take a couple seconds takes 20-30 seconds because of repeated 429 errors.
This happens throughout the day, not just peak hours. Claude models seem to get hit the hardest, but Gemini gets throttled too. The responses always come through eventually, which proves the quota is there — it’s just being artificially delayed.
I upgraded to Ultra specifically to avoid this. If I’m hitting rate limits on a $200/month plan, what exactly am I paying for? The free tier probably has the same experience at this point.
Is anyone else seeing this? Is there a way to get actual priority access that matches what we’re paying for !!!
Hi @Jonathan_Gorce,
Thank you for bringing this to our attention. We sincerely apologize for the inconvenience caused. To help us troubleshoot this issue, could you please provide:
- 2-3 recent timestamps (with your timezone) of when these 429 errors occurred
- The exact error message you see (a screenshot is even better)
- Does this happen even on short, simple prompts, or primarily when sending very large context windows (like entire repos)?
1 Like
The frequency of these service interruptions has become unsustainable. At a monthly rate of $200+, I expect a level of stability that is currently not being met. Please be advised that unless these hourly issues are permanently rectified, I will be terminating my account effective at the end of this billing cycle.
Trajectory ID: b27f4a87-5d71-
Error: HTTP 503 Service Unavailable
Sherlog:
TraceID: 0x9e252c
Headers: {“Alt-Svc”:[“h3=“:443”; ma=2592000,h3-29=“:443”; ma=2592000”],“Content-Length”:[“429”],“Content-Type”:[“text/event-stream”],“Date”:[“Fri, 13 Mar 2026 13:02:42 GMT”],“Server”:[“ESF”],“Server-Timing”:[“gfet4t7; dur=362”],“Vary”:[“Origin”,“X-Origin”,“Referer”],“X-Cloudaicompanion-Trace-Id”:[“9e252cbb04ddb37b”],“X-Content-Type-Options”:[“nosniff”],“X-Frame-Options”:[“SAMEORIGIN”],“X-Xss-Protection”:[“0”]}
{
“error”: {
“code”: 503,
“details”: [
{
“@type”: “type.googleapis.com/google.rpc.ErrorInfo”,
“domain”: “cloudcode-pa.googleapis.com”,
“metadata”: {
“model”: “claude-opus-4-6-thinking”
},
“reason”: “MODEL_CAPACITY_EXHAUSTED”
}
],
“message”: “No capacity available for model claude-opus-4-6-thinking on the server”,
“status”: “UNAVAILABLE”
}
}
Trajectory ID: d2f0a605-39a7-
Error: HTTP 503 Service Unavailable
Sherlog:
TraceID: 0x899e2dc
Headers: {“Alt-Svc”:[“h3=“:443”; ma=2592000,h3-29=“:443”; ma=2592000”],“Content-Length”:[“525”],“Content-Type”:[“text/event-stream”],“Date”:[“Fri, 13 Mar 2026 13:10:22 GMT”],“Server”:[“ESF”],“Server-Timing”:[“gfet4t7; dur=722”],“Vary”:[“Origin”,“X-Origin”,“Referer”],“X-Cloudaicompanion-Trace-Id”:[“899e2dcb96febb5c”],“X-Content-Type-Options”:[“nosniff”],“X-Frame-Options”:[“SAMEORIGIN”],“X-Xss-Protection”:[“0”]}
{
“error”: {
“code”: 503,
“details”: [
{
“@type”: “type.googleapis.com/google.rpc.ErrorInfo”,
“domain”: “cloudcode-pa.googleapis.com”,
“metadata”: {
“model”: “gemini-3.1-pro-high”
},
“reason”: “MODEL_CAPACITY_EXHAUSTED”
},
{
“@type”: “type.googleapis.com/google.rpc.RetryInfo”,
“retryDelay”: “37s”
}
],
“message”: “No capacity available for model gemini-3.1-pro-high on the server”,
“status”: “UNAVAILABLE”
}
}
Every day, every few prompts across all models. I also have Workspace Ultra - had a support ticket open with Google since the end of Feb - yes, it’s been a problem that long.
1 Like
I usually send feedback via the IDE but today:
An error occurred while submitting your feedback. Please try again.
1 Like
This is getting extremely frustrating now, every new updates is a disappointment Google Dev team really need to focus and ensure a smooth experience for everyone, this token ludo is actually getting on our nerves now. Absolutely nothing is clear, the usage, limits, tokens, nothing.
1 Like
