# Inference API model timeout (Flan-UL2)

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finference-api-model-timeout-flan-ul2%2F41045%3E%5C
**Category:** Inference Endpoints on the Hub\
**Created:** [May 26, 2023, 7:09am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finference-api-model-timeout-flan-ul2%2F41045 "2023-05-26T07:09:37Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![abhinav-neil](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/abhinav-neil/32/16348_2.png) [@abhinav-neil](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fabhinav-neil)%5C
**Post date:** [May 26, 2023, 7:09am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finference-api-model-timeout-flan-ul2%2F41045%2F1 "2023-05-26T07:09:37Z")

</div>

I’ve been trying to access the inference API for the model [google/flan-ul2](https://huggingface.co/google/flan-ul2) for the past 2 days, but I keep getting an error 504: response time-out. The model is not loading (the web-UI inference doesn’t work either). The problem persists even after using my access token (pro). Any suggestions?

---

<div class="post-metadata">

**Author:** ![olafvosscv](https://avatars.discourse-cdn.com/v4/letter/o/ba8739/32.png) [@olafvosscv](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Folafvosscv)%5C
**Post date:** [May 26, 2023, 12:11pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finference-api-model-timeout-flan-ul2%2F41045%2F2 "2023-05-26T12:11:13Z")

</div>

Not sure if for the same reasons, but I also couldn’t get endpoints to run on flan-t5-xxl or fan-ul2 on GPU [large] instances. And xlarge wasn’t accessible to me.