Horay.ai

Main Features

Text Generation

Delivers efficient, user-friendly, and scalable LLM models with out-of-the-box inference acceleration capabilities, including Llama3, Mixtral, Qwen, Deepseek, etc.

Embedding/Reranker

Includes a diverse range of Embedding and Reranker models to make your RAG more efficient and straightforward.

Image Generation

Encompasses a diverse range of text-to-image and text-to-video models, such as SDXL, SDXL lightning, photomaker, instantid, and so on.

Voice Generation

Accelerate ASR/TTS models with the latest and greatest technology to generate voices with minimal latency.

Core Advantages

• High speed generation capability
• Ultra-low latency API services
• Out-of-the-box inference acceleration
• Significant cost-effectiveness

Usage

Developers can seamlessly integrate the fastest model services from Horay.ai with just a single line of code.

Typical Applications

• Fast-interacting Agent application based on ultra-low latency
• Real-time responsive chat2DB application utilizing ultra-low latency
• Image generation with significantly reduced costs based on optimized API

Pricing Model

• Pay-as-you-go model
• New users automatically receive free credits
• Serverless inference charged per token
• On-demand deployments charged per GPU usage time
• Enterprise-grade security and reliability requires contacting support@horay.ai

Rate Limits

• Measured in five ways: RPM (requests per minute), RPD (requests per day), TPM (tokens per minute), TPD (tokens per day), and IPM (images per minute)
• Automatically increases spend limit quota to next tier based on historic spend

Getting Started

Sign up at https://dash.horay.ai to receive free credits and start using serverless inference and on-demand deployments.