Play 52
AI API Gateway v2
High✅ Ready
Intelligent API gateway with semantic caching and smart model routing.
Next-generation AI API gateway with semantic caching via Azure Redis, intelligent model routing between GPT-4o and GPT-4o-mini based on query complexity, and token budget enforcement per tenant. Features rate limiting, real-time usage analytics, and cost attribution dashboards. Built on Azure API Management with custom policies for AI-specific traffic patterns.
Architecture Pattern
Gateway pattern: semantic cache layer, model router, token budget enforcement
Azure Services
Azure API ManagementAzure OpenAIAzure Redis CacheAzure MonitorKey Vault
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Gateway Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (232 lines), evaluate (130 lines), tune (211 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with APIM + OpenAI key inputs + envFile
TuneKit (AI Config)
- config/openai.json — model routing thresholds, fallback config
- config/guardrails.json — rate limits, token budgets per tenant
- evaluation/eval.py — Cache hit >60%, Latency p95 <200ms
Tuning Parameters
Cache similarity thresholdModel routing complexity scoreToken budget per tenantRate limit windowFallback model strategy
Estimated Cost
Dev/Test
$60–100/mo
Production
$1.5K–4K/mo