Models

type Models

A list of supported models.

  • "gpt-4o": The GPT-4 OpenAI model.

  • "chatgpt-4o-latest": The latest version of the ChatGPT model.

  • "gpt-4-turbo": The GPT-4 Turbo model.

  • "gpt-4o-2024-08-06": The GPT-4 OpenAI model trained on data up to August 6, 2024.

  • "gpt-4o-mini": The GPT-4 OpenAI model with fewer parameters.

  • "gpt-4": The GPT-4 OpenAI model.

  • "hermes-3-llama-3.1-405b": The Hermes-3 Llama-3.1 model with 405 billion parameters.

  • "gpt-4o-2024-05-13": The GPT-4 OpenAI model trained on data up to May 13, 2024.

  • "gpt-4o-mini-2024-07-18": The GPT-4 OpenAI model with fewer parameters trained on data up to July 18, 2024.

  • "llama-3.1-405b-instruct": The Llama-3.1 model with 405 billion parameters and instruction-based training.

  • "qwen-2-7b-instruct": The Qwen-2 model with 7 billion parameters and instruction-based training.

  • "nous-capybara-7b": The Nous Capybara model with 7 billion parameters.

  • "phi-3-medium-128k-instruct": The Phi-3 model with medium size and instruction-based training.

  • "openchat-7b": The OpenChat model with 7 billion parameters.

  • "llama-3.1-70b-instruct": The Llama-3.1 model with 70 billion parameters and instruction-based training.

  • "toppy-m-7b": The Toppy-M model with 7 billion parameters.

  • "gemma-7b-it": The Gemma model with 7 billion parameters and instruction-based training.

  • "mythomist-7b": The Mythomist model with 7 billion parameters.

  • "phi-3-mini-128k-instruct": The Phi-3 model with mini size and instruction-based training.

  • "gemma-2-9b-it": The Gemma-2 model with 9 billion parameters and instruction-based training.

  • "llama-3-8b-instruct": The Llama-3 model with 8 billion parameters and instruction-based training.

  • "mixtral-8x22b-v0.1": The Mixtral model with 8x22 billion parameters and version 0.1.

  • "mixtral-8x22b-instruct-v0.1": The Mixtral model with 8x22 billion parameters, instruction-based training, and version 0.1.

  • "llama-3-70b-instruct": The Llama-3 model with 70 billion parameters and instruction-based training.

  • "llama-2-70b-chat-hf": The Llama-2 model with 70 billion parameters for chat and high-frequency prompts.

  • "llama-2-13b-chat-hf": The Llama-2 model with 13 billion parameters for chat and high-frequency prompts.

  • "llama-2-7b-chat-hf": The Llama-2 model with 7 billion parameters for chat and high-frequency prompts.

  • "zephyr-7b-beta": The Zephyr model with 7 billion parameters in beta.

  • "llama-3.1-8b-instruct": The Llama-3.1 model with 8 billion parameters and instruction-based training.

  • "mixtral-8x7b-instruct-v0.1": The Mixtral model with 8x7 billion parameters, instruction-based training, and version 0.1.

PreviousClientNextMessages

Last updated