Features
User-pays LLM inference — no developer upfront costs
Drop-in auth components (login, balance, top-ups)
Unified gateway for OpenAI, Anthropic, Google Gemini (100+ models)
Echo SDK replaces Vercel AI SDK with 5-line change
Markup revenue on every token
Universal balance across all Echo-powered apps
No API key management for developers
No Stripe integration required
Real-time balance and usage monitoring per user
Free tier sponsorship for new users
Zero-cost infrastructure (no hosting bills)
Open-source codebase (GitHub)
CLI tool for scaffolding (echo-start)
Templates for Next.js and React
Unified API for 400+ models across 70+ providers
Automatic failover routing when a provider goes down
Model Fusion: combine budget models to rival frontier performance
Subagent delegation: frontier models hand off tasks to cheaper workers
Speech/transcription APIs (May 2026)
Unified Image API with capability discovery across 30+ models (June 2026)
OpenAI SDK compatible out of the box
Server-side presets to survive model deprecation
Edge-deployed for minimal latency
Budget controls and spend limits
Credit-based pricing with no subscriptions
Model routing visualization for latency and cost
Private model support for enterprise deployments
Data policy-based routing and enforcement
MCP server for coding agents (June 2026)
