# Differences in results between Google Gemini Node and direct HTTP Request (Audio Analysis)

**URL:** <https://community.n8n.io/t/differences-in-results-between-google-gemini-node-and-direct-http-request-audio-analysis/259092>\
**Category:** Questions\
**Tags:** gemini\
**Created:** [1 فبراير 2026، 4:06م UTC](https://community.n8n.io/t/differences-in-results-between-google-gemini-node-and-direct-http-request-audio-analysis/259092 "2026-02-01T16:06:57Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![Levan](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/levan/32/156342_2.png) [@Levan](https://community.n8n.io/u/Levan)\
**Post date:** [1 فبراير 2026، 4:06م UTC](https://community.n8n.io/t/differences-in-results-between-google-gemini-node-and-direct-http-request-audio-analysis/259092/1 "2026-02-01T16:06:57Z")

</div>

## Question

I am trying to replicate the behavior of the native Google Gemini “Analyze Audio” node using a manual HTTP Request node([https://aiplatform.googleapis.com/v1/publishers/google/models/gemini-2.5-flash:generateContent](https://aiplatform.googleapis.com/v1/publishers/google/models/gemini-2.5-flash:generateContent)) to hit Vertex AI, but I’m seeing significant differences in results and token usage. I have a few questions about how the native node is configured “under the hood”:

1. What are the default Temperature, Top-P, and Top-K values used by the native node?
2. Does the native node include any hidden System Instructions or “System Prompt” wrappers that aren’t visible in the UI?

## Information on your n8n setup

- **n8n version:** 1.123.18
- **Running n8n via (Docker, npm, n8n cloud, desktop app): cloud**

---

<div class="post-metadata">

**Author:** ![achamm](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/achamm/32/143734_2.png) [@achamm](https://community.n8n.io/u/achamm)\
**Post date:** [1 فبراير 2026، 5:06م UTC](https://community.n8n.io/t/differences-in-results-between-google-gemini-node-and-direct-http-request-audio-analysis/259092/2 "2026-02-01T17:06:29Z")

</div>

Hey @Levan, I checked your link, and it went to a invalid URL - “**This [aiplatform.googleapis.com](http://aiplatform.googleapis.com) page can’t be found**

No webpage was found for the web address: **[https://aiplatform.googleapis.com/v1/publishers/google/models/gemini-2.5-flash:generateContent](https://aiplatform.googleapis.com/v1/publishers/google/models/gemini-2.5-flash:generateContent)**

HTTP ERROR 404”

I also did some research and also checked the [N8N documentation for the node](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-langchain.googlegemini/), and I couldn’t find any details on temperature, Top-P, Top-K either. However, this is just a guest but the default might match the default through the actual correct URL, though I’m not sure.

1. I didnt see any system instructions but you can use the text input to help describe the audio, for a better response. You can also set the max tokens it returns for the analysis description.

 ![Screenshot 2026-02-01 at 12.05.59 PM](https://europe1.discourse-cdn.com/n8n/original/3X/e/0/e013a80e5707053f373c71277b9aa87eba6c59a7.png)

Hope this Helps! If you have any more questions, feel free to ask!

---

<div class="post-metadata">

**Author:** ![mohamed3nan](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/mohamed3nan/32/188347_2.png) [@mohamed3nan](https://community.n8n.io/u/mohamed3nan)\
**Post date:** [1 فبراير 2026، 6:13م UTC](https://community.n8n.io/t/differences-in-results-between-google-gemini-node-and-direct-http-request-audio-analysis/259092/3 "2026-02-01T18:13:34Z")

</div>

Hi @Levan, welcome!

The Gemini node does not use the Vertex endpoints (it uses `https://generativelanguage.googleapis.com`,

> [@Levan](#):
>
> - What are the default Temperature, Top-P, and Top-K values used by the native node?
> - Does the native node include any hidden System Instructions or “System Prompt” wrappers that aren’t visible in the UI?

As per the source code:

> <https://github.com/n8n-io/n8n/blob/89f8fb04ca401517500b6b6100a95ed7578ca0f5/packages/%40n8n/nodes-langchain/nodes/vendors/GoogleGemini/helpers/baseAnalyze.ts#L84>

The only parameter sent is `maxOutputTokens`, which is already an option in the node UI,

also the **Text Input** is sent as part of the body content.

I believe all other settings (Top-P, Top-K, etc.) use the defaults for the `/v1beta/${model}:generateContent` endpoint..

---

<div class="post-metadata">

**Author:** ![system](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/system/32/195824_2.png) [@system](https://community.n8n.io/u/system)\
**Post date:** [2 مايو 2026، 6:13م UTC](https://community.n8n.io/t/differences-in-results-between-google-gemini-node-and-direct-http-request-audio-analysis/259092/4 "2026-05-02T18:13:58Z")

</div>

تم إغلاقه في في 2 مايو 2026، 6:13م UTC

This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.