Product Introduction

Product Overview
Based on excellent foundational models, we provide cost-effective GenAI services.

Product Features
As a one-stop cloud service platform integrating top-tier large models, we are committed to providing developers with faster, cheaper, more comprehensive, and smoother model APIs.

We have already launched various large language models, image generation models, code generation models, vector and reordering models, and multimodal large models.

This allows developers and product managers to achieve "Token Freedom" without worrying about the computing costs incurred during the development phase and large-scale promotion.

We provide out-of-the-box large model inference acceleration services, bringing a more efficient user experience to your GenAI applications.

Quick Start

View the model list and model details

Obtain the API Key and Base URL

Call the API

We are fully aligned with the official OpenAI Docs and OpenAI API Reference, and the usage methods are completely consistent. Based on official Model Endpoint Compatibility:

Where you need to use the OpenAI API, simply replace api.openai.com with the Base_URL obtained from the platform.

Replacement examples:
Official: https://api.openai.com/v1/chat/completions

Our: https://{{Base_URL}}/v1/chat/completions

Please note: Some apps or websites have API_Base as: https://api.openai.com or https://api.openai.com/v1. In this case, it should be replaced with: https://{{Base_URL}} or https://{{Base_URL}}/v1

When calling in code, please note: Regarding the API KEY, in the Authorization parameter of the Header, enter the API KEY generated in the admin backend - API KEYS after Bearer, for example, Bearer sk-xxxxxxx

Product Introduction

Product Introduction#

Quick Start#

Product Introduction

Quick Start