Avatar
openai/gpt-4o
Public
Circuit
Code
Versions
API
RUNNING
The circuit is running and is healthy.
4Total Runs
2,838Avg Response Time (ms)
0Total Embeds
1Total Nodes
0.00%Error Rate
Control Panel
Login to ModelWorksLogin to ModelWorks to use this circuit. To get started, get an API key.
Explore endpointsModelWorks allows apps to access LLMs and MCP servers worldwide easily in any datacenter, securely and privately.
SecretsOverride default secrets and set up your own for better billing and security.
Readme

Open AI Logo

OpenAI (gpt-4o Chat Completion Service

Overview

The OpenAI (gpt-4o) Chat Completion Service generates conversation-based responses using the gpt-4o model. This service allows for customization through parameters like temperature, frequency penalty, and logit bias, ensuring dynamic and tailored chat completions.

Environment Configuration

  • API Key: Ensure the api_key is securely stored in your environment secrets under env.

Inputs

1. Messages (messages)

  • Description: A list of messages comprising the conversation so far.
  • Type: array
  • Required: Yes

2. Store (store)

  • Description: Whether to store the output for model training.
  • Type: boolean
  • Default Value: false
  • Required: No

3. Frequency Penalty (frequency_penalty)

  • Description: Penalize new tokens based on their existing frequency in the text.
  • Type: number
  • Default Value: 0
  • Required: No

4. Presence Penalty (presence_penalty)

  • Description: Penalize new tokens if they already appear in the text so far.
  • Type: number
  • Default Value: 0
  • Required: No

5. Logit Bias (logit_bias)

  • Description: Modify the likelihood of specified tokens appearing in the completion.
  • Type: object
  • Default Value: null
  • Required: No

6. Temperature (temperature)

  • Description: Sampling temperature to use, between 0 and 2.
  • Type: number
  • Default Value: 1
  • Required: No

7. Top-p (top_p)

  • Description: Nucleus sampling with a top-p probability mass.
  • Type: number
  • Default Value: 1
  • Required: No

8. User (user)

  • Description: A unique identifier representing the end user for monitoring abuse.
  • Type: string
  • Default Value: null
  • Required: No

Cost

250 units per request

Notes

  1. Environment Setup: Ensure your api_key is correctly configured by uploading your API KEY in circuit -> settings -> secrets.
  2. Parameter Tuning: Adjust temperature, frequency_penalty, and presence_penalty for varied responses.
  3. User Monitoring: Use the user input for monitoring and preventing abuse.

Enjoy dynamic and responsive chat completions with OpenAI (gpt-4o)!

About
GPT-4o is a versatile multimodal language model that seamlessly integrates text and visual understanding, allowing it to interpret and generate rich descriptions of both written and image-based inputs. It excels at complex reasoning tasks, contextual comprehension, and creative content generation across diverse formats. With robust performance and expanded context handling, GPT-4o powers applications ranging from conversational assistants to detailed image analysis and document summarization.
openai.com/
About the Author
OpenAI is an AI research and deployment company on a mission to ensure that artificial general intelligence (AGI) benefits all of humanity. Founded in 2015, it develops state-of-the-art machine learning models—like GPT for natural language and DALL·E for image generation—and carefully studies their societal impact. Through a capped-profit structure, OpenAI balances rapid innovation with long-term safety research, partnering with organizations worldwide to advance AI responsibly and equitably.
OpenAi
@OPENAI
@openai
https://openai.com/
@OpenAI
Pricing Structure
Base Cost
Fixed
Local
Flat rate per execution2 credits
Token-based Pricing
Usage
Local
Input tokens0.0₅25 credits
Output tokens0.0₄1 credits
Token pricing display: Per TokenPer Token