# Perf

## Docs

- [A/B Testing](https://docs.withperf.pro/advanced/ab-testing.md): Run A/B tests to compare model performance
- [Custom Orchestration Rules](https://docs.withperf.pro/advanced/custom-routing.md): Configure custom orchestration rules for your workloads
- [Enterprise Features](https://docs.withperf.pro/advanced/enterprise.md): Advanced features for enterprise customers
- [Fine-tuning Preferences](https://docs.withperf.pro/advanced/preferences.md): Customize Perf orchestration for your specific needs
- [Audio API](https://docs.withperf.pro/api-reference/audio.md): Text-to-speech (TTS) and speech-to-text (STT) transcription
- [Chat API](https://docs.withperf.pro/api-reference/chat.md): Complete Chat API reference documentation
- [Image Generation](https://docs.withperf.pro/api-reference/images.md): Generate images with DALL-E, Stable Diffusion, Flux, and more
- [Logs](https://docs.withperf.pro/api-reference/logs.md)
- [Metrics](https://docs.withperf.pro/api-reference/metrics.md)
- [Policies API](https://docs.withperf.pro/api-reference/policies.md): Configure routing and content policies for governance and compliance
- [Schema Enforcement](https://docs.withperf.pro/api-reference/schemas.md): Validate, auto-repair, and semantically correct LLM outputs against JSON schemas
- [Streaming API](https://docs.withperf.pro/api-reference/streaming.md): Real-time streaming API documentation
- [Tools API](https://docs.withperf.pro/api-reference/tools.md): Agentic capabilities: Web Search, Documents/RAG, and Memory
- [Video Generation](https://docs.withperf.pro/api-reference/video.md): Generate videos with Veo, Runway, Luma, and Pika
- [Authentication & Security](https://docs.withperf.pro/authentication.md): Learn how to securely authenticate with the Perf API
- [Frequently Asked Questions](https://docs.withperf.pro/faq.md): Common questions about Perf AI Runtime Orchestrator
- [Perf - AI Runtime Orchestrator for LLM Cost Optimization & Quality Control](https://docs.withperf.pro/index.md): Perf is an intelligent AI infrastructure layer that automatically routes LLM requests to optimal models, generates images/audio/video, and enforces output schemas - reducing costs by up to 60% while ensuring quality.
- [Integration Examples](https://docs.withperf.pro/integration-examples.md): Real-world examples of integrating Perf into your application stack
- [Alerts & Notifications](https://docs.withperf.pro/platform/alerts.md): Set up alerts and notifications for your Perf account
- [Analytics](https://docs.withperf.pro/platform/analytics.md)
- [Dashboard](https://docs.withperf.pro/platform/dashboard.md)
- [Team management](https://docs.withperf.pro/platform/team-management.md)
- [Quickstart](https://docs.withperf.pro/quickstart.md): Get up and running with Perf in under 5 minutes
- [Best Practices](https://docs.withperf.pro/resources/best-practices.md): Best practices for using Perf AI Runtime Orchestrator
- [Migration Guide](https://docs.withperf.pro/resources/migration.md): Migrate from your existing LLM setup to Perf
- [JavaScript SDK](https://docs.withperf.pro/sdks/javascript.md): Official Perf SDK for JavaScript and TypeScript
- [Python SDK](https://docs.withperf.pro/sdks/python.md): Official Perf SDK for Python with sync and async support
- [Voice Agents](https://docs.withperf.pro/voice-agents/overview.md): Build conversational voice AI agents with Perf
- [Python Integration](https://docs.withperf.pro/voice-agents/python.md): Server-side Python integration for Perf Voice Agents
- [JavaScript SDK](https://docs.withperf.pro/voice-agents/sdk.md): PerfVoice SDK reference — drop-in voice agent integration for web apps
- [WebSocket Protocol](https://docs.withperf.pro/voice-agents/websocket.md): Raw WebSocket integration for voice agents — full protocol reference

## OpenAPI Specs

- [openapi](https://docs.withperf.pro/openapi.yaml)