Platform Introduction

​

Models and interfaces

• Text large model: supports OpenAI / Anthropic / Gemini compatible interfaces, providing text generation capabilities based on natural language interaction.
• Large speech model, supports OpenAI compatible interface, provides TTS/STT/STS capabilities for natural language interactive generation capabilities.
• Video large model supports Text2Video / Image2Video many scene interfaces, providing users with the ability to generate videos through text descriptions, reference pictures, and video templates.
• Image large model, supports Image Generation interface, providing users with the ability to generate images through text descriptions.
• Music large model supports Music Generation interface, providing users with the ability to generate music through song features and lyrics.

​

Advantages and services

• Leading model performance: Significantly optimizes computing latency, provides excellent performance guarantee for low-latency scenarios, supports over 100 million calls in a single day, and enables rapid iteration at the weekly level.
• High cost performance: Provide a flexible pay-as-you-go model to reduce resource waste and accurately control budgets.
• Agile and easy to use: The interface provides diverse parameters and usage methods and provides a large number of application examples.
• High concurrency throughput: Ultra-large inference cluster supports the application of models to large-scale user products.
• Security compliance: Comply with industry standards and compliance requirements, fully meet the security needs of enterprise-level users, large language model security capabilities + third-party independent audit interface to ensure the security and compliance of output results.
• Expert Team: Top R&D and business teams provide industry-leading AGI technical services and solutions.