Local LLM routing layer for Claude Code, Codex, and OpenCode
Stage
Growing
Startup
Founded
Not given
Not given
Based in
HK
US
Pricing model
Paid
Freemium
Pricing
Per-token billing for text models and per-image/second for media models, with all models priced 20% below official provider rates. Free trial with test credits, no credit card required. Credits roll over indefinitely.
Free: $0 per month with 50M tokens a month and 2 connected devices. Pro: $30 per month with unlimited tokens and 5 connected devices.
Key features
OpenAI-compatible API
Unified billing and credentials
Real-time usage analytics
Budget alerts and cost control
Model comparison tools
Playground for testing
Enterprise-grade security
99.9% service uptime
Sub-400ms average latency
Routes to 293 models from 24 providers
Automatic fallback across providers
Included inference on all plans
End-to-end encrypted key vault
Shared memory across agents
OpenAI and Anthropic compatible APIs
Context.dev integration for web data
Works with Claude Code, Codex, OpenCode and other tools
Browser chat with voice transcription
Cost and usage analytics
What makes it different
20-40% lower pricing than direct provider rates
Single API key replaces multiple vendor accounts
Zero vendor lock-in with instant model switching
No code refactoring required
First request works with no setup or keys required
All your keys and models accessible through one layer
CometAPI
OpenLLM