# Helicone

## Docs

- [Create Evaluator](https://mintlify.wiki/Helicone/helicone/api/evaluations/create.md): Create a new evaluator for scoring LLM responses
- [Query Evaluators](https://mintlify.wiki/Helicone/helicone/api/evaluations/query.md): List all evaluators in your organization
- [Evaluator Stats](https://mintlify.wiki/Helicone/helicone/api/evaluations/scores.md): Get statistics and performance metrics for an evaluator
- [Chat Completions](https://mintlify.wiki/Helicone/helicone/api/gateway/chat-completions.md): Create chat completions using the Helicone AI Gateway
- [List Models](https://mintlify.wiki/Helicone/helicone/api/gateway/models.md): Get available models through the Helicone AI Gateway
- [Create Prompt](https://mintlify.wiki/Helicone/helicone/api/prompts/create.md): Create a new prompt with initial version
- [Get Prompt](https://mintlify.wiki/Helicone/helicone/api/prompts/get.md): Retrieve a specific prompt with its versions
- [Query Prompts](https://mintlify.wiki/Helicone/helicone/api/prompts/query.md): List and filter prompts in your organization
- [Update Prompt](https://mintlify.wiki/Helicone/helicone/api/prompts/update.md): Create a new version of an existing prompt
- [Add Feedback](https://mintlify.wiki/Helicone/helicone/api/requests/feedback.md): Add user feedback ratings to requests
- [Get Request](https://mintlify.wiki/Helicone/helicone/api/requests/get.md): Retrieve a single request by ID
- [Update Properties](https://mintlify.wiki/Helicone/helicone/api/requests/properties.md): Add or update custom properties on requests
- [Query Requests](https://mintlify.wiki/Helicone/helicone/api/requests/query.md): Query and filter requests with advanced filtering and pagination
- [Session Metrics](https://mintlify.wiki/Helicone/helicone/api/sessions/metrics.md): Get aggregated metrics for sessions
- [Query Sessions](https://mintlify.wiki/Helicone/helicone/api/sessions/query.md): Retrieve sessions with filtering and pagination
- [System Architecture](https://mintlify.wiki/Helicone/helicone/architecture.md): Understand how Helicone's architecture delivers reliable LLM observability with minimal latency
- [Alerts](https://mintlify.wiki/Helicone/helicone/features/alerts.md): Get notified when your LLM applications hit error thresholds or cost limits
- [LLM Caching](https://mintlify.wiki/Helicone/helicone/features/caching.md): Store and reuse LLM responses to reduce costs and latency
- [Datasets](https://mintlify.wiki/Helicone/helicone/features/datasets.md): Curate and export LLM request/response data for fine-tuning, evaluation, and analysis
- [Evaluations](https://mintlify.wiki/Helicone/helicone/features/evaluations.md): Evaluate and score LLM outputs to monitor quality, track performance, and improve your applications
- [Custom LLM Rate Limits](https://mintlify.wiki/Helicone/helicone/features/rate-limiting.md): Set custom rate limits for model provider API calls to control usage and prevent abuse
- [Webhooks](https://mintlify.wiki/Helicone/helicone/features/webhooks.md): Receive real-time notifications when LLM requests complete
- [Automatic Fallbacks](https://mintlify.wiki/Helicone/helicone/gateway/fallbacks.md): Build resilient AI applications with automatic provider failover and retry strategies
- [AI Gateway Overview](https://mintlify.wiki/Helicone/helicone/gateway/overview.md): Use any LLM provider through a single OpenAI-compatible API with intelligent routing, fallbacks, and unified observability
- [Prompt Management](https://mintlify.wiki/Helicone/helicone/gateway/prompt-integration.md): Deploy and iterate prompts through the AI Gateway without code changes
- [Provider Routing](https://mintlify.wiki/Helicone/helicone/gateway/provider-routing.md): Automatic model routing across 100+ providers for reliability and performance
- [Gateway Quickstart](https://mintlify.wiki/Helicone/helicone/gateway/quickstart.md): Make your first request through the AI Gateway in under 5 minutes
- [Track and Optimize LLM Costs](https://mintlify.wiki/Helicone/helicone/guides/cost-tracking.md): Step-by-step guide to implementing comprehensive cost tracking and optimization for your LLM application
- [Export LLM Request Data from Helicone](https://mintlify.wiki/Helicone/helicone/guides/data-export.md): Complete guide to exporting request/response data for analysis, backup, and compliance
- [Debug LLM Applications with Helicone](https://mintlify.wiki/Helicone/helicone/guides/debugging-llm-apps.md): Step-by-step tutorial for debugging production LLM issues using Helicone's observability tools
- [Track Environments in LLM Applications](https://mintlify.wiki/Helicone/helicone/guides/environment-tracking.md): Best practices for tracking development, staging, and production LLM requests with Helicone
- [Evaluate RAG Applications with RAGAS](https://mintlify.wiki/Helicone/helicone/guides/evaluation-with-ragas.md): Step-by-step tutorial for integrating RAGAS evaluation scores with Helicone for RAG observability
- [Prepare Data for Fine-Tuning with Helicone](https://mintlify.wiki/Helicone/helicone/guides/fine-tuning-prep.md): Use Helicone production data to create high-quality fine-tuning datasets
- [Monitoring AI Agents with Sessions](https://mintlify.wiki/Helicone/helicone/guides/monitoring-ai-agents.md): Step-by-step tutorial for tracking multi-step AI agent workflows with Helicone Sessions
- [Production Monitoring for LLM Applications](https://mintlify.wiki/Helicone/helicone/guides/production-monitoring.md): Comprehensive guide to monitoring LLM applications in production with Helicone
- [Anthropic Integration](https://mintlify.wiki/Helicone/helicone/integrations/anthropic.md): Integrate Helicone with Anthropic Claude models
- [LangChain Integration](https://mintlify.wiki/Helicone/helicone/integrations/langchain.md): Integrate Helicone with LangChain for full chain observability
- [OpenAI Integration](https://mintlify.wiki/Helicone/helicone/integrations/openai.md): Integrate Helicone with OpenAI for complete observability
- [Integration Overview](https://mintlify.wiki/Helicone/helicone/integrations/overview.md): Connect Helicone with your favorite LLM providers and frameworks
- [Vercel AI SDK Integration](https://mintlify.wiki/Helicone/helicone/integrations/vercel-ai-sdk.md): Integrate Helicone with Vercel AI SDK for streaming and edge support
- [Welcome to Helicone](https://mintlify.wiki/Helicone/helicone/introduction.md): Open-source LLM observability platform and AI Gateway for production applications
- [Custom Properties](https://mintlify.wiki/Helicone/helicone/observability/custom-properties.md): Add custom metadata to LLM requests for powerful segmentation, filtering, and analysis
- [Observability Overview](https://mintlify.wiki/Helicone/helicone/observability/overview.md): Monitor, analyze, and optimize your LLM applications with comprehensive observability features
- [Request Logging](https://mintlify.wiki/Helicone/helicone/observability/requests.md): Capture and analyze every LLM request with detailed metrics and metadata
- [Session Tracking](https://mintlify.wiki/Helicone/helicone/observability/sessions.md): Group related LLM requests to track multi-turn conversations and user workflows
- [Distributed Tracing](https://mintlify.wiki/Helicone/helicone/observability/traces.md): Visualize and debug complex LLM workflows with parent-child request relationships
- [User Metrics](https://mintlify.wiki/Helicone/helicone/observability/user-metrics.md): Track costs, usage, and performance per user to understand user behavior and optimize spend
- [Prompt Deployment](https://mintlify.wiki/Helicone/helicone/prompts/deployment.md): Deploy prompts to different environments and manage production releases
- [Prompt Management Overview](https://mintlify.wiki/Helicone/helicone/prompts/overview.md): Centralize, version, and deploy your LLM prompts without code changes
- [SDK Integration](https://mintlify.wiki/Helicone/helicone/prompts/sdk-integration.md): Integrate Helicone prompts into your application using the TypeScript SDK
- [Prompt Versioning](https://mintlify.wiki/Helicone/helicone/prompts/versioning.md): Track changes, create versions, and manage your prompt evolution
- [Quickstart Guide](https://mintlify.wiki/Helicone/helicone/quickstart.md): Get your first LLM request logged with Helicone in under 2 minutes
- [Docker Deployment](https://mintlify.wiki/Helicone/helicone/self-hosting/docker.md): Deploy Helicone using Docker with either the all-in-one container or Docker Compose for development and production environments.
- [Kubernetes Deployment](https://mintlify.wiki/Helicone/helicone/self-hosting/kubernetes.md): Deploy Helicone on Kubernetes using Helm charts for scalable, production-ready LLM observability infrastructure.
- [Self-Hosting Helicone](https://mintlify.wiki/Helicone/helicone/self-hosting/overview.md): Deploy and manage your own instance of Helicone with full control over your LLM observability infrastructure.