AI API relay station providing access to multiple AI models with unified billing
Stage
Not given
Startup
Founded
Not given
2026
Based in
Not given
Not given
Pricing model
Paid
Paid
Pricing
Not given
Pay-as-you-go with Alipay top-ups. Minimum charge ¥10, exchange rate ¥1 = $1 credit. Pricing varies by model and group: GPT models from $0.02 input / $0.12 output per million tokens in the 0.1x group; Claude models from $0.50 input / $3.00 output per million tokens in the 0.4x group; Grok models ava
Key features
Adapter registry with 191+ production-ready fine-tunes for discovery
In-browser A/B testing playground to compare adapters against base models
One-click deployment to serverless API endpoints with OpenAI-compatible format
Multi-adapter serving on single base model with zero cold starts
Automated fine-tuning with Unsloth-optimized kernels
Creator monetization with per-token revenue sharing
IP protection with managed endpoints and no public weight downloads
Framework integration as OpenAI-compatible proxy
Group-based API key management with separate billing multipliers from 0.1x to 0.7x
Unified balance across multiple AI model providers
OpenAI-compatible endpoint requiring only Base URL change
Support for Claude Messages interface for Claude models
Anytime balance withdrawal with no fees
Base64 image input support
What makes it different
2x-5x faster fine-tuning using Unsloth-optimized kernels compared to traditional methods
Creators earn 70% revenue share on every token served through their adapters
Lowest pricing multipliers in the market at 0.1x baseline
Unified billing across different model providers with single balance
No withdrawal fees for unused balance
Simple integration with only Base URL change needed