Features
Automatic API key injection for OpenAI, Anthropic, Google Gemini
Automatic base URL override to route via AI Gateway
Proxy requests without managing provider accounts
Token-based rate limiting (TPM) per model
Unified credit billing across AI providers
Usage analytics dashboard in Netlify UI
Native integration with Netlify Functions, Edge Functions, Preview Servers
Support for official client libraries (OpenAI SDK, Anthropic SDK, Google GenAI SDK)
Support for official REST APIs
Works with web frameworks (Astro, TanStack Start, Next.js, Gatsby, Nuxt)
Claude Fable 5, Claude Sonnet 5, Gemini 2.5 Pro, Gemini 3.1 Flash-Lite Image support
No prompt storage or model output storage
Opt-out option for auto-injection
Local development support via Netlify CLI and Netlify Vite plugin
Vision/multimodal support for image understanding
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)
