ngrok AI Gateway
Route model requests with shared access controls and observability
AI models & model access
Explore foundation models and services that provide model access.
Cuey
Compare AI answers and carry useful context between supported assistants
Opper AI
Access and govern AI models through a unified gateway
discode.ai
Use multiple AI models through a chat interface with routing controls
Auriko
Route and monitor model inference with provider and budget controls
ZeroGPU
Run specialized AI workloads across edge and cloud infrastructure
Zro
Hosted inference endpoints for coding agents and compatible API clients
TrustedRouter
Route model requests with explicit privacy and spending controls
Inferock
Measure AI inference quality, usage, and failures across deployment options
Experiential Labs
Route hosted and self-managed AI models through one gateway
GoModel
Self-host an AI gateway with routing, budgets, and usage logs
Hopscotch
Access AI models through one API with spending and usage controls
FastRouter
Route model requests through a shared API with usage and cost controls
Weave Router
Route coding-agent work across models and provider subscriptions
MiniMax
AI models and APIs for language, speech, video, and creative work
Gemini Robotics
AI models for robotic perception, planning, and physical action
Novita AI
Model APIs, agent sandboxes, and GPU infrastructure for AI applications
DeepInfra
Hosted AI inference APIs with a catalog of models and GPU options
Replicate
Run, fine-tune, and deploy AI models through an API
Cerebras
AI inference services built on wafer-scale computing