🌐 AI Gateway

Route all your AI traffic through a single, secure endpoint. Support for 12 providers with smart routing, caching, and cost optimization.

Overview

The AI Gateway is an OpenAI-compatible proxy that sits between your application and LLM providers. Send requests to a single endpoint and CloudVera handles provider routing, security scanning, caching, cost tracking, and failover — all at the edge with sub-20ms overhead.

Streaming

Stream responses in real-time using Server-Sent Events (SSE). Set stream: true in your request and iterate over chunks as they arrive. Works with all providers.

Function & Tool Calling

Define tools (functions) that the model can invoke, then handle the results. CloudVera proxies tool calls transparently — works with OpenAI, Anthropic, Google, Mistral, and any provider that supports function calling.

Supported Providers

CloudVera supports 12 AI providers through a unified API. Each provider's models are accessible through the same endpoint.

Smart Routing

Intelligent model routing with automatic failover, circuit breakers, and latency-based selection.

Semantic Caching

Save 30-50% on costs by caching semantically similar requests. When a request matches a previous response, CloudVera returns the cached result instantly.

Virtual API Keys

Create scoped API keys with granular permissions, model allow-lists, budgets, and rate limits. Every proxy request is checked against the key's permissions before reaching the provider.

A/B Testing & Canary

Experiment with different models and providers to find the best combination of quality, cost, and latency for your use case.

Workers AI Specialized Models

Access 30+ Cloudflare Workers AI models for tasks beyond chat and embeddings — summarization, translation, image generation, speech-to-text, text-to-speech, classification, object detection, and more. These models use the /v1/run endpoint instead of /v1/chat/completions.