Chat API Overview

Chat API is designed to be fully compatible with the OpenAI Chat Completion endpoint, making it easy for you to integrate advanced conversational AI into your applications.

Introduction to Large Language Model

Large Language Models (LLMs) refer to the state-of-the-art deep learning models for text generation, capable of producing high-quality textual completions, easily adapted to interactive chat setting and able to analyze and utilize tools for more complicated tasks. Below is an example of a completed conversation of the prompt "tell me a joke".

Prompt: tell me a joke

Completion: Why couldn't the bicycle stand up by itself? Because it was two-tired!

Usually, language models accept messages in the format of

"messages": [
    {
      "role": "user",
      "content": "Tell me a joke"
    },
    {
      "role": "assistant",
      "content": "Why couldn't the bicycle stand up by itself? Because it was two-tired!"
    }
  ]

You can see details and try our API in the API Reference tab.

Getting Started

First, create an account on our platform to get your API key Get an API Key

API Overview

Our chat models are served via a REST API, adhering to the Chat Completion standard popularized by OpenAI. There are two modes:

• Standard mode. This mode processes the entire input and returns a complete JSON response. It's ideal for most typical use cases where you need a single, comprehensive reply from the AI.
• Streaming mode. This mode allows for real-time streaming of responses. This is particularly useful for applications requiring low latency and immediate feedback, such as live chat interfaces.