Context I’m building a children’s storybook app that generates 4 comic panel images per story using gemini-2.5-flash-image via Vertex AI. The app flow is: User captures a drawing AI interprets the drawing (text-only, works fine) Backend generates 4 comic panels sequentially (one after another, not…

I started hitting the same thing in the last few days with gemini-2.5-flash-image after months of no issue. Also seems to happen on the third sequential request. It seems like something changed on Google’s side.

Eu também to com o mesmo problema mas não com história e sim com edição de imagem ele edita uma imagem modifica 2 veze na 3x pra alterar, ele dá a mensagem: " Retry-After" e You’ve reached your rate limit. Please try again later. Não mostra o tempo mas como estou testando outras janelas, limpo o …

That’s interesting, thanks for sharing. Yes, seems strange that it’s failing so consistently. That doesn’t quite match with my understanding of what 429s should indicate (ie actual resource exhaustion of a global quota shared between all Vertex AI pay-as-you-go users).

I agree it seems odd. I found these other recent threads which appear to be related: [image] Urgent help with 429 gemini-3-pro-image-preview Gemini API I started seeing a massive spike in 429s for gemini-2.5-flash-image as well, much more than typical. It star…

Likewise, this has been hitting us pretty hard since ~1/22, where it spiked significantly. I’ve tried the approaches listed here also. We’re likewise generating a batch of several images per workflow. Our absolute daily volume is relatively low though, so it’s not like we’re not spamming the model. …

Yes, exactly. I’m lucky to be in early-stage dev phase with no angry customers yet. Since provisioned throughput isn’t really an option unless my app (against all odds) become a commercial success, I guess I’ll have to look at a fall-back provider for the image gen. It’s disappointing since it’s st…

Update: Moved to OpenRouter as a workaround Wanted to share an update in case it helps others stuck on this. I ended up migrating my backend from direct Vertex AI calls to routing through OpenRouter, which provides an OpenAI-compatible API that can seamlessly fall back between Vertex AI and AI Stud…

Gemini-2.5-flash-image: Frequent 429 RESOURCE_EXHAUSTED during sequential image generation - seeking clarity on rate limits

Gemini API

tylertreat January 27, 2026, 3:07pm 5

I agree it seems odd. I found these other recent threads which appear to be related:

Topic		Replies	Views
Sudden Spike in 429 Errors with Gemini 2.5 via Vertex AI Global Endpoint Gemini API vertexai , gemini	7	1370	April 8, 2026
Spike in 429 RESOURCE_EXHAUSTED with v1beta1 StreamGenerateContent (Gemini 3 Flash Preview / Vertex global) — quotas look fine Gemini API gemini-api , live-streaming , gemini-3	3	439	February 18, 2026
Gemini-3.1-flash-image-preview on Vertex AI — 429 RESOURCE_EXHAUSTED on every request Gemini API vertexai	0	149	April 5, 2026
429 RESOURCE_EXHAUSTED at 0.03% of quota — reproducible across projects, tiers and endpoints Gemini API rate-limits	22	441	August 18, 2026
Issue with 429 Error on Gemini API Despite Staying Within Rate Limits Gemini API gemini-api	14	2149	June 5, 2026

Gemini-2.5-flash-image: Frequent 429 RESOURCE_EXHAUSTED during sequential image generation - seeking clarity on rate limits

Related topics