# External Inference using google vertex ai and gemini-3.6-flash error

**URL:** <https://discuss.elastic.co/t/external-inference-using-google-vertex-ai-and-gemini-3-6-flash-error/390296>\
**Category:** Elastic Agent\
**Created:** [September 10, 2026, 7:37am UTC](https://discuss.elastic.co/t/external-inference-using-google-vertex-ai-and-gemini-3-6-flash-error/390296 "2026-09-10T07:37:50Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![tallakh](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/tallakh/32/8860_2.png) [@tallakh](https://discuss.elastic.co/u/tallakh)\
**Post date:** [September 10, 2026, 7:37am UTC](https://discuss.elastic.co/t/external-inference-using-google-vertex-ai-and-gemini-3-6-flash-error/390296/1 "2026-09-10T07:37:50Z")

</div>

Hi!

I'm trying to set up an external inference using our Google vertex ai account and the model gemini-3.6-flash. The inference creation works, but trying to use it as a chat-completion fails with an error:

```auto
Error: Received an unsuccessful status code for request from inference
entity id [googlevertexai-chat_completion-example] status [400].

Function call is missing a thought_signature in functionCall parts.
This is required for tools to work correctly, and missing
thought_signature may lead to degraded model performance.

Additional data:
function call `default_api:platform_core_list_indices`, position 2.

```

We are on Elastic Cloud Hosted using version 9.5.2

---

<div class="post-metadata">

**Author:** ![bmorelli25](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/bmorelli25/32/38738_2.png) [@bmorelli25](https://discuss.elastic.co/u/bmorelli25)\
**Post date:** [September 11, 2026, 2:43am UTC](https://discuss.elastic.co/t/external-inference-using-google-vertex-ai-and-gemini-3-6-flash-error/390296/2 "2026-09-11T02:43:31Z")

</div>

Hey @tallakh. Unfortunately there's a compatibility limitation with Gemini 3. You'll need to use a Gemini 2.x model such as `gemini-2.5-flash`. I'll improve our public-facing documentation around this limitation this while the eng team looks at improving compatibility for newer models.

---

<div class="post-metadata">

**Author:** ![tallakh](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/tallakh/32/8860_2.png) [@tallakh](https://discuss.elastic.co/u/tallakh)\
**Post date:** [September 11, 2026, 7:13am UTC](https://discuss.elastic.co/t/external-inference-using-google-vertex-ai-and-gemini-3-6-flash-error/390296/3 "2026-09-11T07:13:06Z")

</div>

Thanks @bmorelli25 Hope this will be fixed soon, Gemini 2.x models feels a bit ancient 🙂