# GPT Live 1 Livekit Inference Not Working? **URL:** \ **Category:** Getting Started\ **Tags:** livekit-inference\ **Created:** [October 19, 2026, 2:13pm UTC](https://community.livekit.io/t/gpt-live-1-livekit-inference-not-working/2297 "2026-10-19T14:13:17Z")\ **Posts on this page:** 8\ **Page:** 1
**Author:** ![chase\_fagen](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/chase_fagen/32/1003_2.png) [@chase\_fagen](https://community.livekit.io/u/chase_fagen)\ **Post date:** [October 19, 2026, 2:13pm UTC](https://community.livekit.io/t/gpt-live-1-livekit-inference-not-working/2297/1 "2026-10-19T14:13:18Z")
Hello, I see in Livekit 1.8.8 Python Livekit Inference is supposed to Support GPT Live but I keep getting **HTTP 503**. ---
**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:** [October 19, 2026, 3:38pm UTC](https://community.livekit.io/t/gpt-live-1-livekit-inference-not-working/2297/2 "2026-10-19T15:38:17Z")
I just tested with the attached, and it seems to work: [agent.py](https://community.livekit.io/uploads/short-url/fHWmrAxTpaOHwNeH2yUvPqQOqVe.py) (5.8 KB) There haven’t been any outages that could explain the 503, which I assume would have been an issue between our backend and OpenAI. Did you specify `inference.DuplexModel` ? ---
**Author:** ![chase\_fagen](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/chase_fagen/32/1003_2.png) [@chase\_fagen](https://community.livekit.io/u/chase_fagen)\ **Post date:** [October 19, 2026, 4:01pm UTC](https://community.livekit.io/t/gpt-live-1-livekit-inference-not-working/2297/3 "2026-10-19T16:01:18Z")
I tested your full `agent.py` unchanged using `livekit-agents==1.8.8` and our LiveKit project credentials. The agent connected to the room and received test audio, but `inference.DuplexModel(model="openai/gpt-live-1")` failed to connect after retries. I also captured the underlying handshake response: {“code”:“model\_unavailable”,“message”:“requested gpt-live model is unavailable”,“type”:“server\_error”} With the same credentials, `openai/gpt-realtime-2.1` connects successfully. We’re using the default production inference endpoint with no override. Failing request ID: `dbd33686-eee5-4b55-a19a-8929e189c943` Timestamp: October 19, 2026, at 15:57:19 UTC. ---
**Author:** ![chase\_fagen](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/chase_fagen/32/1003_2.png) [@chase\_fagen](https://community.livekit.io/u/chase_fagen)\ **Post date:** [October 19, 2026, 6:50pm UTC](https://community.livekit.io/t/gpt-live-1-livekit-inference-not-working/2297/4 "2026-10-19T18:50:02Z")
Could it be a ZDR HIPAA thing that is enabled on my account? ---
**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:** [October 20, 2026, 7:55am UTC](https://community.livekit.io/t/gpt-live-1-livekit-inference-not-working/2297/5 "2026-10-20T07:55:57Z")
Good catch, it’s HIPAA related. Your workspace is marked as HIPAA required, but I checked the code as the source of truth and the model is not served to HIPAA-compliant workspaces. The ‘official’ list is [HIPAA Eligible Products and Services | LiveKit](https://livekit.com/legal/hipaa) . I see internal discussions that the team are working on this, but please don’t take that as a guarantee the model will at some stage be allowed on HIPAA-complaint workspaces, though obviously we would like it to. I’m more concerned about your confusing error message - I thought we had a dedicated error for this, something like ‘model will not be served to a HIPAA-complaint project’. Let me look into that separately. Note that all LiveKit Inference models are ZDR, including this one, so this was not related to ZDR. ---
**Author:** ![chase\_fagen](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/chase_fagen/32/1003_2.png) [@chase\_fagen](https://community.livekit.io/u/chase_fagen)\ **Post date:** [October 20, 2026, 7:28pm UTC](https://community.livekit.io/t/gpt-live-1-livekit-inference-not-working/2297/6 "2026-10-20T19:28:56Z")
Yes I think a better error code would be helpful. Was banging my head trying to figure out what I was doing wrong! Hopefully will be compliant soon! ---
**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:** [October 21, 2026, 9:23am UTC](https://community.livekit.io/t/gpt-live-1-livekit-inference-not-working/2297/7 "2026-10-21T09:23:26Z")
> [@chase\_fagen](#): > > Yes I think a better error code would be helpful. Non-compliant pipeline models DO give a helpful error, it’s just realtime models that do not (hence my confusion earlier). So, we need to address that. ---
**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:** [October 23, 2026, 9:24am UTC](https://community.livekit.io/t/gpt-live-1-livekit-inference-not-working/2297/8 "2026-10-23T09:24:13Z")
This topic was automatically closed 2 days after the last reply. New replies are no longer allowed.