Low-cost AI model API gateway for DeepSeek, GLM, Kimi, Qwen and MiniMax with one API key
Production Ready Cloud with Low Cost
Stage
Startup
Startup
Founded
2026
2024
Based in
HK
US
Pricing model
Paid
Paid
Pricing
Token-based billing with no subscription. Minimum top-up $1. First top-up of $10 gets $10 bonus; $60 gets $20 bonus; $100 gets $30 bonus; $200+ gets $50 bonus. DeepSeek V4 Flash: $0.084 per 1M input tokens, $0.168 per 1M output tokens. GLM-5.3 Flash: $0.105 per 1M input, $0.350 per 1M output. MiniMa
Pay-as-you-go pricing for serverless inference charged per token and for on-demand deployments charged per GPU usage time. New users receive free credits. Text models range from $0.05 to $1.5 per 1M tokens (input and output), including Llama-3.2-1B-Instruct at $0.06/1M tokens, Meta-Llama-3.1-8B-Inst
Key features
OpenAI and Anthropic compatible endpoints
Token-based billing with no subscription
Models from DeepSeek, GLM, Kimi, Qwen and MiniMax
Credits that do not expire while account is active
Usage tracking and dashboard management
Pricing 10-50% below official vendor rates
Direct sourcing from official vendor platforms
Account scheduling and health checks for reliability
Minimum $1 top-up with no top-up fees
Top-up bonus credits on purchases
Text generation with multiple LLM models including Llama, Qwen, and DeepSeek
Embedding and reranking models for RAG applications
Text-to-image and text-to-video generation
Voice generation with ASR/TTS models
Single line of code integration
Agent application with ultra-low latency
Chat2DB application with real-time responsiveness
Inference acceleration capability
Competitive pricing with reduced costs
What makes it different
Lowest prices available: 10-50% below official vendor rates for the same models
Credits never expire while account remains active
Compatible with existing OpenAI and Anthropic integrations
Out-of-the-box inference acceleration capability
Fast model updates and comprehensive model selection
Single line of code integration with no deployment complexity