# Images disabled for Gemma via LiveKit Inference

**URL:** <https://community.livekit.io/t/images-disabled-for-gemma-via-livekit-inference/1997>\
**Category:** Agents\
**Tags:** python, agent-deployment, llm, livekit-inference\
**Created:** [September 4, 2026, 12:18am UTC](https://community.livekit.io/t/images-disabled-for-gemma-via-livekit-inference/1997 "2026-09-04T00:18:16Z")\
**Posts on this page:** 6\
**Page:** 1

<div class="post-metadata">

**Author:** ![Muhammad\_Khalid](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/muhammad_khalid/32/2426_2.png) [@Muhammad\_Khalid](https://community.livekit.io/u/Muhammad_Khalid)\
**Post date:** [September 4, 2026, 12:18am UTC](https://community.livekit.io/t/images-disabled-for-gemma-via-livekit-inference/1997/1 "2026-09-04T00:18:17Z")

</div>

Hi there! We’ve been using Gemma via LiveKit Inference in production since August 24th around 5pm PDT. Before deploying the Gemma-powered agent to production we tested it internally including uploading images which Gemma was able to handle natively completely fine. For less than a day after our deployment to production, users were able to upload images completely fine. On August 25th around 8:55 am PDT we started getting this error in our logs:

```auto
APIStatusError: message='image input is not enabled: message 24 contains image_url content but image (vision) input is currently disabled for this model', status_code=400, retryable=False, body=image input is not enabled: message 24 contains image_url content but image (vision) input is currently disabled for this model

```

We didn’t change anything on our end and were wondering whether there were some changes with livekit’s Gemma deployment through LiveKit Inference affecting image handling.

---

<div class="post-metadata">

**Author:** ![darryncampbell](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/darryncampbell/32/20_2.png) [@darryncampbell](https://community.livekit.io/u/darryncampbell)\
**Post date:** [September 4, 2026, 9:20am UTC](https://community.livekit.io/t/images-disabled-for-gemma-via-livekit-inference/1997/2 "2026-09-04T09:20:51Z")

</div>

Looks like image support was removed because of stability issues.

I would (personally) classify image support as an ‘undocumented feature’ during the initial rollout, since we never claimed support for it in the [docs](https://docs.livekit.io/agents/models/llm/livekit/).

Let me see if I can get an official word on Images for Gemma via LiveKit Inference, to see if it’s on the roadmap.

---

<div class="post-metadata">

**Author:** ![darryncampbell](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/darryncampbell/32/20_2.png) [@darryncampbell](https://community.livekit.io/u/darryncampbell)\
**Post date:** [September 4, 2026, 3:57pm UTC](https://community.livekit.io/t/images-disabled-for-gemma-via-livekit-inference/1997/3 "2026-09-04T15:57:09Z")

</div>

@Muhammad_Khalid it is indeed on the roadmap 🙂

I think the team will do this very soon, I’ll keep an eye on our internal ticket.

---

<div class="post-metadata">

**Author:** ![Cecchi\_MacNaughton](https://avatars.discourse-cdn.com/v4/letter/c/e9a140/32.png) [@Cecchi\_MacNaughton](https://community.livekit.io/u/Cecchi_MacNaughton)\
**Post date:** [September 4, 2026, 5:26pm UTC](https://community.livekit.io/t/images-disabled-for-gemma-via-livekit-inference/1997/4 "2026-09-04T17:26:07Z")

</div>

Hi @darryncampbell - this is useful clarification. I do think it’s worth calling out this limitation on the docs. None of the model/provider pages in Livekit’s docs specifically mention multimodal capabilities, and since Gemma is itself a multimodal model it seemed reasonable to assume those capabilities would work as they do with other inference providers.

---

<div class="post-metadata">

**Author:** ![darryncampbell](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/darryncampbell/32/20_2.png) [@darryncampbell](https://community.livekit.io/u/darryncampbell)\
**Post date:** [September 7, 2026, 9:55am UTC](https://community.livekit.io/t/images-disabled-for-gemma-via-livekit-inference/1997/5 "2026-09-07T09:55:05Z")

</div>

> [@Cecchi\_MacNaughton](#):
>
> I do think it’s worth calling out this limitation on the docs. None of the model/provider pages in Livekit’s docs specifically mention multimodal capabilities, and since Gemma is itself a multimodal model it seemed reasonable to assume those capabilities would work as they do with other inference providers.

Thanks, that’s fair feedback. And the other way also - once we get Images re-enabled we should also have a code sample in the docs showing how to use them.

---

<div class="post-metadata">

**Author:** ![system](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/system/32/26_2.png) [@system](https://community.livekit.io/u/system)\
**Post date:** [September 22, 2026, 9:55am UTC](https://community.livekit.io/t/images-disabled-for-gemma-via-livekit-inference/1997/6 "2026-09-22T09:55:25Z")

</div>

This topic was automatically closed 15 days after the last reply. New replies are no longer allowed.