GPT 4 Models - Workflow AI in Stack

Table of Contents

• Overview of the Enhancement
• New Features
  • Select Model
  • GPT Models Compared
  • Select Action Type
• Using This Feature
• Pricing

Overview of the Enhancement

We've upgraded the existing action and introduced several new enhancements to make the GPT action in Stack workflows more powerful. You can now leverage the capabilities of GPT 4 at the same cost as the previous GPT 3 models.

New Features

Select Model

With the introduction of new models, you can now choose from the following:

• GPT 4 Turbo
• GPT 4o
• GPT 4o Mini

By default, the model selected will be GPT 4o, but you can opt for GPT 3.5 Turbo from the dropdown menu if preferred.

GPT Models Compared

Model	Description	Performance Highlights	Cost per Execution
GPT 3.5 Turbo	Not as advanced as 4 Turbo	Good responses, may struggle with complex queries	$0.015
GPT-4 Turbo	More advanced and powerful	Consistent and accurate, handles complex queries	$0.03
GPT-4o	Optimized for specific tasks	Effective for most queries, balanced speed	$0.03
GPT-4o Mini	Lightweight version of GPT-4o	Fastest response time, efficient for basic needs	$0.015

Select Action Type

If you're unsure about which prompt to use, try one of our pre-made action types. These come with auto-populated prompts that can be used directly:

1. Analyze Text Sentiment
2. Summarize Text
3. Translate
4. Custom

Using This Feature

To start using this feature in your Stack workflows:

1. Click the "+" icon and search for "GPT powered by OpenAI".
2. Select your desired model.
3. Choose the Custom action type if you wish to write your own prompt.
4. Alternatively, select any other action type to use pre-populated prompts.

Pricing

• GPT 4o & GPT 4 Turbo: $0.03 per execution
• GPT 4o Mini: $0.015 per execution

Enjoy the enhanced capabilities of GPT 4 models in your Stack workflows to achieve more efficient and powerful results!