Features
OpenAI-compatible endpoint
Real-time provider benchmarking (price, latency, load)
Automatic cheapest/fastest routing
Support for closed and open LLMs
Restrict routing to specific providers
Performance constraint configuration
List all available models & family models
MakeHub Tools Layer for custom tooling
Direct integration with Cline and Roo Code forks
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)
