AI API relay station providing access to multiple AI models with unified billing
Infrastructure for real-time AI agents
Stage
Startup
Established
Founded
2026
2009
Based in
Not given
US
Pricing model
Paid
Paid
Pricing
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
Voice AI Agents: from $0.05 per minute. Text-to-Speech: from $0.000003 per character. Speech-to-Text: from $0.0015 per minute. Voice API: from $0.002 per minute. SIP Trunking: from $0.0032 per minute. SMS and MMS: from $0.004 per message. WhatsApp: from $0.0025 per minute. Email API: from $0.30 per
Key features
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
Voice AI agents with speech-to-text, text-to-speech, and inference on one control plane
Serverless and dedicated GPU inference with 50+ open-source models
Edge compute with Functions, Stateful Actors, KV, SQLDB, and Object Storage at 20+ points of presence
Global phone numbers, toll-free numbers, and number porting
Owned carrier infrastructure with 25+ points of presence and 30+ carrier licenses
OpenAI SDK compatible inference API with streaming and tool calling
Agent SDK for building stateful AI agents with memory and scheduled tasks
What makes it different
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
Only licensed carrier that owns AI infrastructure end-to-end including private network, GPUs, and edge compute
Everything on one control plane and one bill without multiple vendors
Inference runs colocated with media plane on owned GPUs with no egress fees