TABLE OF CONTENTS
What is this enhancement?
We have revamped the current action and added multiple new enhancements. This new enhancement will make the GPT action extremely powerful and users will be able to use the power of GPT 4 in the workflows at same price we were offering GPT 3.
What are the new feature?
Select Model
New models launched are
- GPT 4 Turbo
- GPT 4o
- GPT 4o mini
Users will be able to select from a "Model" to select from. By default GPT 4o will be selected but the users will have the option to select GPT 3.5 Turbo from the dropdown.
GPT Models Compared
GPT 3.5 Turbo | GPT-4 Turbo | GPT-4o | GPT-4o Mini |
---|---|---|---|
Not as good as 4 turbo | More advanced and powerful | Optimized for specific tasks | Lightweight version of GPT-4o |
Good responses | Consistent and accurate responses | Consistent with slight trade-offs | Efficient but less comprehensive |
Not that consistent | Can handle highly complex queries | Handles most queries effectively | Best for less complex queries |
May struggle to connect the dots | A bit slower than GPT-4o Mini | Balanced speed and performance | Fastest in response time |
Faster responses | Superior contextual understanding | Good contextual understanding | Adequate for basic needs |
$0.015 per execution | $0.03 per execution | $0.03 per execution | $0.015 per execution |
Select Action Type
Don't know what prompt to use, try some of our pre made action types. The prompt will auto populate and the action can be used based on that. Below options are available to select from
1. Analyze Text Sentiment
2. Summarize Text
3. Translate
4. Custom
How to use this feature?
- Click the "+" icon and search for "GPT powered by OpenAI"
- Select the Model
- Use Custom action type if you want to write the prompt
- Use Any other Action type to get pre populated prompts
Pricing
GPT 4o & GPT 4 Turbo - $0.03 per execution
GPT 4o mini GPT 3.5 Turbo - $0.015 per execution
Was this article helpful?
That’s Great!
Thank you for your feedback
Sorry! We couldn't be helpful
Thank you for your feedback
Feedback sent
We appreciate your effort and will try to fix the article