StarMagic
HomeModelsAgents
Solutions
Growth & Marketing
  • Content GenerationDraft marketing copy, blogs, and short-video scripts in one click
  • Image CreationFull-chain visual asset production for marketing, eCommerce, and games
  • Video GenerationScript → storyboard → video, end to end
Efficiency & Collaboration
  • Code AssistantThe 24/7 teammate engineers need every day
  • Data AnalyticsAsk data in natural language; get structured results and charts
  • Knowledge ManagementEnterprise knowledge base + RAG to retain team wisdom
Customer & Interaction
  • AI Customer Service24/7 multilingual, explainable conversational support
  • Voice InteractionReal-time voice agents for phone calls and in-car systems

End-to-end AI implementation · data, vision, and customer workflows

View all solutions →
FranchiseDocs
HomeModelsAgents
Solutions
  • AI Customer Service
  • Content Generation
  • Code Assistant
  • Data Analytics
  • Image Creation
  • Video Generation
  • Voice Interaction
  • Knowledge Management
FranchiseDocs
…
StarMagic

Access 500+ leading AI models with unified APIs, billing, and management—so AI becomes real productivity.

© 2026 DATANEST LIMITED. STARMAGIC . All rights reserved

Product

  • Models
  • Agents

Resources

  • Tutorials
  • Inspiration

Support

  • Log in
  • Dashboard

One gateway for the world’s leading AI models

Access 500+ text, image, video, and audio models with usage-based billing and direct contract pricing. Open any card to view integration docs, SDK examples, and pricing details.

https://api.hotrouter.ai/v1
Get API key

Models

1 models available

AllBytePlusOpenAIAnthropicGoogle GeminiDeepSeekAlibaba QwenMoonshot AI / KimixAIZhipu AI / GLMTencent Hunyuan
AllTextImageAudioVideo
02M
$0$50
  • -35%

    Tencent Hy3

    Per token

    Hy3 is a 295B-parameter Mixture-of-Experts language model from Tencent (21B active parameters, 192 experts with top-8 routing, plus a 3.8B MTP layer), developed by the Tencent Hy Team and released under Apache 2.0. Refined on the Hy3 preview release with improved post-training data and scaled RL, it targets reasoning, agentic workflows, coding and long-context tasks, supporting a 256K context window, hybrid fast/slow thinking via a configurable reasoning_effort parameter, function calling, structured output and caching. It is served on Tencent Cloud TokenHub with an OpenAI-compatible API.

    Input$0.086/M
    Output$0.343/M