# Please allow better AI models in markdown template automations
**URL:** https://community.fibery.io/t/please-allow-better-ai-models-in-markdown-template-automations/9028
**Category:** Bugs & Issues
**Created:** [June 22, 2025, 4:14pm UTC](https://community.fibery.io/t/please-allow-better-ai-models-in-markdown-template-automations/9028 "2025-06-22T16:14:44Z")
**Posts on this page:** 9
**Page:** 1
### Author:  [@Yuri\_BC](https://community.fibery.io/u/Yuri_BC)
#### Post date: [June 22, 2025, 4:14pm UTC](https://community.fibery.io/t/please-allow-better-ai-models-in-markdown-template-automations/9028/1 "2025-06-22T16:14:44Z")
4o-latest is insufficient for most of the analysis of large content.
Please allow to choose a better AI model with a larger token window.
GPT-4o has a **4,096 token output limit** despite having a 128k context window. This is a **known limitation** that affects all GPT-4o implementations.
---
### Author:  [@mdubakov](https://community.fibery.io/u/mdubakov)
#### Post date: [June 23, 2025, 7:41am UTC](https://community.fibery.io/t/please-allow-better-ai-models-in-markdown-template-automations/9028/2 "2025-06-23T07:41:32Z")
> [@Yuri\_BC](#):
>
> GPT-4o
It is chatgpt-4o-latest model in fact and it has 16,384 max output tokens
---
### Author:  [@Chr1sG](https://community.fibery.io/u/Chr1sG)
#### Post date: [June 23, 2025, 11:22am UTC](https://community.fibery.io/t/please-allow-better-ai-models-in-markdown-template-automations/9028/3 "2025-06-23T11:22:24Z")
---
### Author:  [@Chr1sG](https://community.fibery.io/u/Chr1sG)
#### Post date: [June 23, 2025, 12:44pm UTC](https://community.fibery.io/t/please-allow-better-ai-models-in-markdown-template-automations/9028/4 "2025-06-23T12:44:13Z")
---
### Author:  [@Yuri\_BC](https://community.fibery.io/u/Yuri_BC)
#### Post date: [June 23, 2025, 12:55pm UTC](https://community.fibery.io/t/please-allow-better-ai-models-in-markdown-template-automations/9028/5 "2025-06-23T12:55:03Z")
> [@mdubakov](#):
>
> It is chatgpt-4o-latest model in fact and it has 16,384 max output tokens
Yes Fibery’s AI automation uses chatgpt-4o-latest thus configured with a **total** context window of ~16,384 tokens.
But this still runs into issues in most of my cases, e.g. when analyzing large transcripts:
- My **input text** (e.g., the transcript),
- The **markdown template** content,
- The **system prompt** (added behind the scenes),
- And the **model’s response** (output tokens). ← !
This means:
If I give it a very long transcript (e.g. 13,000 tokens), the model has very little room left to generate output (only ~3,000 tokens or less). If the output is complex or lengthy (e.g., summaries, structured extraction), it always runs into issues.
I have spent weeks trying to work around this issue. Now I’m fed up and suggest Fibery solves it with a choice of model, because its such a common need (also for example when analyzing ai chats)
---
### Author:  [@Yuri\_BC](https://community.fibery.io/u/Yuri_BC)
#### Post date: [June 23, 2025, 12:59pm UTC](https://community.fibery.io/t/please-allow-better-ai-models-in-markdown-template-automations/9028/6 "2025-06-23T12:59:44Z")
I now see this new feature, but what model does the Smart Agent use here?
---
### Author:  [@Chr1sG](https://community.fibery.io/u/Chr1sG)
#### Post date: [June 23, 2025, 1:03pm UTC](https://community.fibery.io/t/please-allow-better-ai-models-in-markdown-template-automations/9028/7 "2025-06-23T13:03:38Z")
> [@Yuri\_BC](#):
>
> Yes Fibery’s AI automation uses chatgpt-4o-latest thus configured with a **total** context window of ~16,384 tokens.
Where did you get that from? Everywhere I look says that gpt-4o-latest has a context window of 128k tokens with a 16k output window
---
### Author:  [@Yuri\_BC](https://community.fibery.io/u/Yuri_BC)
#### Post date: [June 23, 2025, 1:17pm UTC](https://community.fibery.io/t/please-allow-better-ai-models-in-markdown-template-automations/9028/8 "2025-06-23T13:17:22Z")
You are right, and I apologize for the confusion 😬
Still:
- Seen the problems I encounter still with Gpt-4o **the issue is not proving the token window** but more the overall capacity to handle complex input and output.
- When Using Grok and Claude Sonnet the issues don’t appear, but that requires my manual handling and copy pasting.
- Anyhow, I hope that Fibery will allow users to specify the model always, wherever AI is used.
- Also, hopefully Fibery will allow for GPT‑4.1 (plus mini and nano variants) which support up to 1 million tokens of context.
---
### Author:  [@mdubakov](https://community.fibery.io/u/mdubakov)
#### Post date: [June 23, 2025, 1:30pm UTC](https://community.fibery.io/t/please-allow-better-ai-models-in-markdown-template-automations/9028/9 "2025-06-23T13:30:40Z")
> [@Yuri\_BC](#):
>
> I now see this new feature,
> but what model does the Smart Agent use here?
Claude Sonnet 4