# Gemini Interactions API

**URL:** https://meta.discourse.org/t/gemini-interactions-api/409240
**Category:** Announcements
**Tags:** ai
**Created:** [4 augustus 2026 om 07:30 UTC](https://meta.discourse.org/t/gemini-interactions-api/409240 "2026-08-04T07:30:21Z")
**Posts on this page:** 1
**Showing post:** 1

<div class="post-metadata">

### Author: ![sam](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/sam/32/102149_2.png) [@sam](https://meta.discourse.org/u/sam)
#### Post date: [4 augustus 2026 om 07:30 UTC](https://meta.discourse.org/t/gemini-interactions-api/409240/1 "2026-08-04T07:30:21Z")

</div>

We just added support for the new [Gemini Interactions API](https://ai.google.dev/gemini-api/docs/interactions-overview) into Discourse AI and recommend you use it for all Gemini Inference.

The `generateContent` API remains in Discourse and is now labeled `Google Gemini (Legacy API)`

All new Gemini LLM providers should use the `Google Gemini` provider and the: `https://generativelanguage.googleapis.com/v1/interactions` endpoint.

### Caveats

The new interactions API no longer allows setting “no thinking” on 2.5 flash models. This was never advisable for reasoning models anyway.

### New Features

The new provider ships with 3 new feature:

1. Tool call streaming (which improves web artifact interactivity)
2. Code execution (native tool)
3. Google Maps (native tool)

In addition to the existing (Search and Fetch tools)

Code execution:

 ![code execution can be used to visualize data](https://global.discourse-cdn.com/meta/original/4X/1/5/2/152f057ddac0679b531c5ac19b659b88be106d60.jpeg)

Maps:

 ![image](https://global.discourse-cdn.com/meta/original/4X/8/c/7/8c7234179fc022a94f73dc1f32a9b15ba08ae8cc.png)

---

_[View the full topic](https://meta.discourse.org/t/gemini-interactions-api/409240)._