Skip to main content

OpenAI

Requisites​

To use OpenAI models, you need to have the following credential information. You can get them by signing up at OpenAI.

Required credentials:

  • OPENAI_API_KEY: Your OpenAI API Key for authentication.

Optional credentials:

  • OPENAI_ORG_ID: Your OpenAI Organization ID, which can be found on your organization settings page.

Supported Models:​

All models provided by Anthropic has the following properties:

  • Function call: Supported
  • Streaming: Supported

All models accept the following extra configs when generating texts:

  • temperature
  • top_p
  • max_tokens
  • stop

GPT 3.5 Series​

GPT-3.5 Turbo​

  • Model schema id: openai/gpt-3.5-turbo
  • Input token limit: 16385
  • Output token limit: 4096

GPT-3.5 Turbo 16k​

  • Model schema id: openai/gpt-3.5-turbo-16k
  • Input token limit: 16385
  • Output token limit: 4096

GPT-4 Series​

GPT-4 is more creative and collaborative than ever before. It can generate, edit, and iterate with users on creative and technical writing tasks, such as composing songs, writing screenplays, or learning a user’s writing style.

GPT-4 is capable of handling over 25,000 words of text, allowing for use cases like long form content creation, extended conversations, and document search and analysis.

GPT-4​

  • Model schema id: openai/gpt-4
  • Input token limit: 8192
  • Output token limit: 4096

GPT-4 Turbo​

  • Model schema id: openai/gpt-4-turbo
  • Input token limit: 128000
  • Output token limit: 4096

GPT-4 Vision​

  • Model schema id: openai/gpt-4-vision
  • Vision: Supported
  • Input token limit: 128000
  • Output token limit: 4096