# Gemini-3.8-live rejected with vertexai=True in livekit-plugins-google, although Vertex AI serves it (EU multi-region) **URL:** \ **Category:** Agents\ **Tags:** realtime\ **Created:** [October 2, 2026, 9:54am UTC](https://community.livekit.io/t/gemini-3-8-live-rejected-with-vertexai-true-in-livekit-plugins-google-although-vertex-ai-serves-it-eu-multi-region/2179 "2026-10-02T09:54:18Z")\ **Posts on this page:** 5\ **Page:** 1
**Author:** ![Akiniesta](https://avatars.discourse-cdn.com/v4/letter/a/ac8455/32.png) [@Akiniesta](https://community.livekit.io/u/Akiniesta)\ **Post date:** [October 2, 2026, 9:54am UTC](https://community.livekit.io/t/gemini-3-8-live-rejected-with-vertexai-true-in-livekit-plugins-google-although-vertex-ai-serves-it-eu-multi-region/2179/1 "2026-10-02T09:54:18Z")
Hi LiveKit community, We run a realtime voice agent on Gemini Live (google.realtime.RealtimeModel), currently gemini-3.1-flash-live-preview through the Gemini Developer API. We want to move it to Vertex AI in the EU multi-region for data residency and enterprise terms. gemini-3.8-live is the natural target, but the plugin blocks it before any connection is made. Versions - livekit-agents 1.8.3 - livekit-plugins-google 1.8.3 (we also checked main at the time of writing: same code) - google-genai 2.25.0 Repro from livekit.plugins import google llm = google.realtime.RealtimeModel( model=“gemini-3.8-live”, vertexai=True, project=“”, location=“eu”, ) Result ValueError: Model ‘gemini-3.8-live’ is a Gemini API model, but vertexai=True. Use a VertexAI model (e.g., ‘gemini-live-2.5-flash-native-audio’) or set vertexai=False. This comes from \_validate\_model\_api\_match() in realtime/realtime\_api.py: gemini-3.8-live and gemini-3.8-live-extended-thinking are listed only in KNOWN\_GEMINI\_API\_MODELS, while KNOWN\_VERTEXAI\_MODELS only contains gemini-live-2.5-flash-native-audio. Vertex AI does serve this model. We called google-genai directly (client.aio.live.connect, vertexai=True, service account with roles/aiplatform.user, no allowlist request) on 2026-10-01: gemini-3.8-live: - eu: works - us: works - europe-west4: 1008 “Publisher model … was not found” - global: 1008 “Publisher model … was not found” gemini-live-2.5-flash-native-audio: - europe-west4: works - eu: 1008 “Publisher model … was not found” On eu, gemini-3.8-live streamed audio replies normally over 8 test sessions, and responded faster than 3.1 on the Developer API in the same conditions (median 1.07 s vs 1.29 s from end of user speech to first audio chunk). The plugin itself also lists gemini-3.8-live in api\_proto.py and applies 3.8-specific handling (MODELS\_WITHOUT\_REPLY\_PLACEHOLDER, MODELS\_DEFAULT\_NON\_BLOCKING), so the rest of the code path looks ready. Suggested fix gemini-3.8-live (and probably gemini-3.8-live-extended-thinking) is available on both APIs. The validation should only raise for models that exist on one side only, for example: KNOWN\_VERTEXAI\_ONLY\_MODELS = frozenset({“gemini-live-2.5-flash-native-audio”}) KNOWN\_GEMINI\_API\_ONLY\_MODELS = frozenset({ “gemini-3.1-flash-live-preview”, “gemini-2.5-flash-native-audio-preview-12-2025”, }) KNOWN\_DUAL\_API\_MODELS = frozenset({ “gemini-3.8-live”, “gemini-3.8-live-extended-thinking”, }) \_validate\_model\_api\_match() would then skip KNOWN\_DUAL\_API\_MODELS. It might also help to mention in the docs that the Live API on Vertex is not available on global, and that 3.8 Live is served on the eu / us multi-regions rather than single regions like europe-west4. A related difference you may want to handle On the Gemini Developer API, gemini-3.8-live rejects thinking\_config=ThinkingConfig(thinking\_level=…) with 1007 Thinking level is not supported for this model. On Vertex eu, the same config was accepted. If the plugin forwards thinking\_config as-is, this difference between the two APIs is worth documenting. Questions 1. Is a fix planned to accept gemini-3.8-live with vertexai=True? We’re happy to open a PR along the lines above if that helps. 2. Until it ships, what is the recommended way to use it on Vertex without patching the plugin? Thanks! ---
**Author:** ![Kamal\_Moha](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/kamal_moha/32/402_2.png) [@Kamal\_Moha](https://community.livekit.io/u/Kamal_Moha)\ **Post date:** [October 2, 2026, 11:47am UTC](https://community.livekit.io/t/gemini-3-8-live-rejected-with-vertexai-true-in-livekit-plugins-google-although-vertex-ai-serves-it-eu-multi-region/2179/2 "2026-10-02T11:47:20Z")
Hi @Akiniesta, I have been able to use `gemini-3.8-live`in Livekit using the Gemini API by setting the `GOOGLE_API_KEY` env variable. And it has been working fine. I’m trying to understand what your issue is. I would like to ask, have you tried using the model `gemini-3.8-live `in Livekit using Gemini Live API before moving it to Vertex. If yes, has that worked for you? When using Vertex to authenticate, you will have to provide `GOOGLE_APPLICATION_CREDENTIALS` with the proper roles. I believe you’re doing that. From the error messages you’ve provided, it shows that `gemini-3.8-live` is accepted by Livekit when using the Gemini API, but Livekit is rejecting it when using Vertex. Is that correct? But when you used `gemini-3.8-live` with google genai, both Gemini API & Vertex. Is that correct? > [@Akiniesta](#): > > On the Gemini Developer API, gemini-3.8-live rejects thinking\_config=ThinkingConfig(thinking\_level=…) with 1007 Thinking level is not supported for this model. Yes, this is right. I agree that this should be highlighted in the Livekit Docs. ---
**Author:** ![Akiniesta](https://avatars.discourse-cdn.com/v4/letter/a/ac8455/32.png) [@Akiniesta](https://community.livekit.io/u/Akiniesta)\ **Post date:** [October 2, 2026, 11:59am UTC](https://community.livekit.io/t/gemini-3-8-live-rejected-with-vertexai-true-in-livekit-plugins-google-although-vertex-ai-serves-it-eu-multi-region/2179/3 "2026-10-02T11:59:28Z")
Hi, thanks for looking into this! To answer your questions: 1. Gemini API (GOOGLE\_API\_KEY): yes, gemini-3.8-live works for us too, both directly with google-genai and through the LiveKit plugin (google.realtime.RealtimeModel, livekit-plugins-google 1.8.3). In the plugin, generate\_reply() works, and so do replies to user audio streamed in real time. 2. LiveKit rejects it with Vertex: correct. The error is raised by the plugin itself, before any network call or credential check: ValueError: Model ‘gemini-3.8-live’ is a Gemini API model, but vertexai=True. Use a VertexAI model (e.g., ‘gemini-live-2.5-flash-native-audio’) or set vertexai=False. It comes from \_validate\_model\_api\_match() in livekit/plugins/google/realtime/realtime\_api.py: gemini-3.8-live and gemini-3.8-live-extended-thinking are listed only in KNOWN\_GEMINI\_API\_MODELS, while KNOWN\_VERTEXAI\_MODELS only contains gemini-live-2.5-flash-native-audio. We checked main as well and the lists are the same. It isn’t an authentication issue: with the same service account (roles/aiplatform.user, via GOOGLE\_APPLICATION\_CREDENTIALS), gemini-live-2.5-flash-native-audio works fine on Vertex through the plugin. 3. google-genai directly, on both APIs: correct. With the same service account and vertexai=True, gemini-3.8-live streams audio replies normally with location=“eu” (8 out of 8 test sessions) and location=“us”. It returns 1008 Publisher model … was not found on global and europe-west4, so it seems to be served on the multi-regions only. So the model works on both APIs at the Google level. Only the plugin’s model/API validation prevents using it with vertexai=True. Minimal repro (livekit-agents / livekit-plugins-google 1.8.3): from livekit.plugins import google google.realtime.RealtimeModel( model=“gemini-3.8-live”, vertexai=True, project=“”, location=“eu”, ) # → ValueError before any connection Suggested fix: treat models served by both APIs as valid for either, and only raise for models that exist on one side. For example: KNOWN\_VERTEXAI\_ONLY\_MODELS = frozenset({“gemini-live-2.5-flash-native-audio”}) KNOWN\_GEMINI\_API\_ONLY\_MODELS = frozenset({ “gemini-3.1-flash-live-preview”, “gemini-2.5-flash-native-audio-preview-12-2025”, }) KNOWN\_DUAL\_API\_MODELS = frozenset({ “gemini-3.8-live”, “gemini-3.8-live-extended-thinking”, }) \_validate\_model\_api\_match() would then skip KNOWN\_DUAL\_API\_MODELS. It might also be worth mentioning in the docs that the Live API on Vertex isn’t available on global, and that 3.8 Live is served on the eu / us multi-regions. One related difference: on the Gemini API, gemini-3.8-live rejects thinking\_config=ThinkingConfig(thinking\_level=…) with 1007 Thinking level is not supported for this model, while Vertex eu accepted the same config. Worth knowing if the plugin forwards thinking\_config as-is. We’re happy to open a PR along these lines if that helps. Until then, is there a recommended way to use gemini-3.8-live on Vertex without patching the plugin? Thanks again! ---
**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 2, 2026, 1:02pm UTC](https://community.livekit.io/t/gemini-3-8-live-rejected-with-vertexai-true-in-livekit-plugins-google-although-vertex-ai-serves-it-eu-multi-region/2179/4 "2026-10-02T13:02:44Z")
Thanks, for reporting. I can reproduce this and I’ve raised this with our agents team. I’m not sure if a separate table for `KNOWN_DUAL_API_MODELS` would be the right approach - I’m not a maintainer of the code, but that feels like one more thing to keep up to date manually. Claude did suggest a workaround which seems to work in my testing, to provide what is (as far as I can tell) an undocumented model name: ```python model="publishers/google/models/gemini-3.8-live", vertexai=True, ``` Good catch on the difference on thinking\_config behaviour, I’ve also raised that with the agents team as it will surely affect how we properly handle the fix for this. ---
**Author:** ![Akiniesta](https://avatars.discourse-cdn.com/v4/letter/a/ac8455/32.png) [@Akiniesta](https://community.livekit.io/u/Akiniesta)\ **Post date:** [October 2, 2026, 1:46pm UTC](https://community.livekit.io/t/gemini-3-8-live-rejected-with-vertexai-true-in-livekit-plugins-google-although-vertex-ai-serves-it-eu-multi-region/2179/5 "2026-10-02T13:46:18Z")
> [@darryncampbell](#): > > Thanks, for reporting. I can reproduce this and I’ve raised this with our agents team. > > I’m not sure if a separate table for `KNOWN_DUAL_API_MODELS` would be the right approach - I’m not a maintainer of the code, but that feels like one more thing to keep up to date manually. > > Claude did suggest a workaround which seems to work in my testing, to provide what is (as far as I can tell) an undocumented model name: > > ```python > model="publishers/google/models/gemini-3.8-live", > vertexai=True > > ``` Thanks a lot @Darryn ! I confirm the workaround works on our side: publishers/google/models/gemini-3.8-live with vertexai=True and location=“eu”, through google.realtime.RealtimeModel (livekit-plugins-google 1.8.3). Both generate\_reply() and replies to streamed user audio work over several runs. We’ll use it until the fix lands and switch back to the plain model name then. Agreed on the dual-API table, a model registry that doesn’t need manual upkeep would be better. Thanks for raising the thinking\_config difference too.