# Helicone

## Docs

- [Authentication](https://mintlify.wiki/helicone/helicone/api/authentication.md): Learn how to authenticate requests to the Helicone API
- [Create Evaluation](https://mintlify.wiki/helicone/helicone/api/evals/create.md): Create a new evaluation score for a specific request
- [Query Evaluations](https://mintlify.wiki/helicone/helicone/api/evals/query.md): Search and filter through evaluation results with advanced filtering capabilities
- [Get Evaluation Scores](https://mintlify.wiki/helicone/helicone/api/evals/scores.md): Retrieve all unique evaluation score names for your organization
- [Chat Completions](https://mintlify.wiki/helicone/helicone/api/gateway/chat-completions.md): Create chat completions using any supported LLM provider
- [List Models](https://mintlify.wiki/helicone/helicone/api/gateway/models.md): Get a list of all supported models across providers
- [API Overview](https://mintlify.wiki/helicone/helicone/api/introduction.md): Introduction to the Helicone REST API
- [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 prompt by ID
- [Query Prompts](https://mintlify.wiki/helicone/helicone/api/prompts/query.md): Search and filter prompts
- [Update Prompt](https://mintlify.wiki/helicone/helicone/api/prompts/update.md): Create a new version of an existing prompt
- [Get Prompt Versions](https://mintlify.wiki/helicone/helicone/api/prompts/versions.md): Retrieve all versions of a prompt
- [Add Feedback to Request](https://mintlify.wiki/helicone/helicone/api/requests/feedback.md): Add thumbs up/down feedback to a specific request
- [Get Request by ID](https://mintlify.wiki/helicone/helicone/api/requests/get.md): Retrieve a specific request by its ID
- [Add Properties to Request](https://mintlify.wiki/helicone/helicone/api/requests/properties.md): Add or update custom properties on a request after it has been created
- [Query Requests](https://mintlify.wiki/helicone/helicone/api/requests/query.md): Query and filter requests with advanced filtering and pagination
- [Add Scores to Request](https://mintlify.wiki/helicone/helicone/api/requests/scores.md): Add evaluation scores to a request for detailed quality metrics
- [Add Session Feedback](https://mintlify.wiki/helicone/helicone/api/sessions/feedback.md): Submit user feedback ratings for specific sessions
- [Query Session Metrics](https://mintlify.wiki/helicone/helicone/api/sessions/metrics.md): Retrieve detailed performance metrics and statistical distributions for sessions
- [Query Sessions](https://mintlify.wiki/helicone/helicone/api/sessions/query.md): Search and filter through session data with advanced filtering options
- [Query User Metrics](https://mintlify.wiki/helicone/helicone/api/users/metrics.md): Retrieve detailed user metrics with advanced filtering and pagination
- [Query Users](https://mintlify.wiki/helicone/helicone/api/users/query.md): Retrieve aggregated user data based on user IDs and time filters
- [Create Webhook](https://mintlify.wiki/helicone/helicone/api/webhooks/create.md): Create a new webhook to receive real-time notifications for your requests
- [Delete Webhook](https://mintlify.wiki/helicone/helicone/api/webhooks/delete.md): Delete an existing webhook configuration
- [List Webhooks](https://mintlify.wiki/helicone/helicone/api/webhooks/list.md): Retrieve all webhooks configured for your organization
- [Datasets](https://mintlify.wiki/helicone/helicone/evaluation/datasets.md): Create evaluation and fine-tuning datasets from production LLM traffic
- [User Feedback](https://mintlify.wiki/helicone/helicone/evaluation/feedback.md): Collect user satisfaction signals to understand and improve LLM response quality
- [Evaluation & Testing Overview](https://mintlify.wiki/helicone/helicone/evaluation/overview.md): Build, evaluate, and improve your LLM applications with datasets, scores, and feedback
- [Evaluation Scores](https://mintlify.wiki/helicone/helicone/evaluation/scores.md): Track evaluation metrics from any framework for centralized LLM observability
- [Alerts](https://mintlify.wiki/helicone/helicone/features/alerts.md): Get notified via email or Slack when metrics exceed thresholds
- [Response Caching](https://mintlify.wiki/helicone/helicone/features/caching.md): Reduce API costs by up to 90% with intelligent response caching
- [Rate Limiting](https://mintlify.wiki/helicone/helicone/features/rate-limiting.md): Control API usage per user, team, or custom segment with flexible rate limits
- [Security & Compliance](https://mintlify.wiki/helicone/helicone/features/security.md): Enterprise-grade security with SOC 2 compliance, encryption, and secure key management
- [Webhooks](https://mintlify.wiki/helicone/helicone/features/webhooks.md): Receive real-time notifications for requests, alerts, and events in your system
- [Automatic Fallbacks](https://mintlify.wiki/helicone/helicone/gateway/fallbacks.md): Configure automatic failover strategies for reliable AI applications
- [Getting Started](https://mintlify.wiki/helicone/helicone/gateway/getting-started.md): Start using Helicone AI Gateway in 2 minutes
- [Integrations](https://mintlify.wiki/helicone/helicone/gateway/integrations.md): Use Helicone AI Gateway with your favorite frameworks and tools
- [AI Gateway Overview](https://mintlify.wiki/helicone/helicone/gateway/overview.md): Access 100+ AI models through one unified API with intelligent routing, automatic fallbacks, and unified observability
- [Prompt Integration](https://mintlify.wiki/helicone/helicone/gateway/prompt-integration.md): Use prompts stored in Helicone with the AI Gateway
- [Provider Routing](https://mintlify.wiki/helicone/helicone/gateway/routing.md): Understand how Helicone routes requests across AI providers
- [Agent Tracing & Observability](https://mintlify.wiki/helicone/helicone/guides/agent-tracing.md): Track complex agent workflows with sessions, tool calls, and decision paths for complete observability
- [Cost Tracking & Optimization](https://mintlify.wiki/helicone/helicone/guides/cost-tracking.md): Monitor LLM spending, optimize costs across providers, and understand unit economics for your AI applications
- [Debugging LLM Applications](https://mintlify.wiki/helicone/helicone/guides/debugging.md): Identify errors, diagnose issues, and optimize LLM application performance with Helicone's debugging tools
- [Running LLM Experiments](https://mintlify.wiki/helicone/helicone/guides/experiments.md): A/B test prompts, models, and parameters with production data to continuously improve response quality
- [Fine-Tuning LLMs with Helicone](https://mintlify.wiki/helicone/helicone/guides/fine-tuning.md): Prepare datasets, manage fine-tuning jobs, and track custom model performance with Helicone and OpenPipe
- [Helicone Guides](https://mintlify.wiki/helicone/helicone/guides/overview.md): Practical guides for building production-ready LLM applications with Helicone's observability platform
- [LLM Evaluation with RAGAS](https://mintlify.wiki/helicone/helicone/guides/tutorials/ragas-evals.md): Implement comprehensive evaluation pipelines using RAGAS metrics and Helicone for systematic quality assessment
- [Structured Outputs with OpenAI](https://mintlify.wiki/helicone/helicone/guides/tutorials/structured-outputs.md): Build reliable LLM applications using OpenAI's function calling and structured outputs with monitoring
- [Multi-Model AI Assistant with Vercel AI Gateway](https://mintlify.wiki/helicone/helicone/guides/tutorials/vercel-ai-gateway.md): Build a customer support assistant that intelligently routes queries to different models based on complexity with cost tracking
- [Anthropic Integration](https://mintlify.wiki/helicone/helicone/integrations/anthropic.md): Integrate Helicone with Anthropic Claude for monitoring and observability
- [Async Logging](https://mintlify.wiki/helicone/helicone/integrations/async-logging.md): Zero-latency logging with @helicone/async and OpenLLMetry
- [LangChain Integration](https://mintlify.wiki/helicone/helicone/integrations/langchain.md): Integrate Helicone with LangChain for observability and monitoring
- [OpenAI Integration](https://mintlify.wiki/helicone/helicone/integrations/openai.md): Integrate Helicone with OpenAI for monitoring and observability
- [Integrations Overview](https://mintlify.wiki/helicone/helicone/integrations/overview.md): Connect Helicone with your favorite AI providers and frameworks
- [Vercel AI SDK Integration](https://mintlify.wiki/helicone/helicone/integrations/vercel-ai-sdk.md): Integrate Helicone with Vercel AI SDK for monitoring and observability
- [Introduction to Helicone](https://mintlify.wiki/helicone/helicone/introduction.md): Open-source AI Gateway and LLM observability platform for building production AI applications with reliability, visibility, and control
- [Custom Properties](https://mintlify.wiki/helicone/helicone/observability/custom-properties.md): Tag LLM requests with custom metadata using headers to enable powerful filtering, segmentation, and cost analysis by any dimension
- [Metrics & Analytics](https://mintlify.wiki/helicone/helicone/observability/metrics.md): Analyze aggregate metrics across requests, sessions, and users to understand system-wide performance, costs, and usage patterns
- [Observability Overview](https://mintlify.wiki/helicone/helicone/observability/overview.md): Comprehensive observability for your LLM applications - monitor requests, track sessions, analyze metrics, and debug AI workflows
- [Requests](https://mintlify.wiki/helicone/helicone/observability/requests.md): View, search, and analyze every LLM request with complete request/response bodies, performance metrics, and custom metadata
- [Sessions](https://mintlify.wiki/helicone/helicone/observability/sessions.md): Track multi-step AI workflows by grouping related requests into sessions - perfect for agents, chatbots, and complex LLM pipelines
- [Traces](https://mintlify.wiki/helicone/helicone/observability/traces.md): Log custom traces for non-LLM operations like database queries, API calls, and tool executions to get complete visibility into your AI workflows
- [Platform Overview](https://mintlify.wiki/helicone/helicone/platform-overview.md): Understand Helicone's architecture and how the AI Gateway, observability platform, and core services work together
- [Prompt Deployment](https://mintlify.wiki/helicone/helicone/prompts/deployment.md): Deploy prompt versions to environments and use them through the SDK or AI Gateway
- [Prompt Experiments](https://mintlify.wiki/helicone/helicone/prompts/experiments.md): Run A/B tests and experiments to compare prompt versions and measure performance
- [Prompt Management Overview](https://mintlify.wiki/helicone/helicone/prompts/overview.md): Version, deploy, and manage AI prompts without code changes using Helicone's prompt management system
- [Prompt Versioning](https://mintlify.wiki/helicone/helicone/prompts/versioning.md): Create, manage, and track prompt versions with semantic versioning and commit history
- [Quick Start](https://mintlify.wiki/helicone/helicone/quick-start.md): Get your first LLM request logged with Helicone in under 2 minutes using the AI Gateway
- [Architecture](https://mintlify.wiki/helicone/helicone/self-hosting/architecture.md): Understanding Helicone's architecture and how services work together
- [Docker Deployment](https://mintlify.wiki/helicone/helicone/self-hosting/docker.md): Deploy Helicone with Docker and Docker Compose
- [Kubernetes Deployment](https://mintlify.wiki/helicone/helicone/self-hosting/kubernetes.md): Deploy Helicone to Kubernetes using Helm charts
- [Self-Hosting Overview](https://mintlify.wiki/helicone/helicone/self-hosting/overview.md): Deploy Helicone on your own infrastructure with full control over your data