Skip to main content

Helicone OSS LLM Observability home page

Models
Discord
Github
Dashboard
Dashboard

Documentation
API Reference
Guides
FAQ

Getting Started

Quickstart
Platform Overview

AI Gateway

Overview
Provider Routing
Prompt Management
Caching
Custom Rate Limits
LLM Security
Large Context

Observability & Analytics

Custom Properties
Sessions
User Metrics
Cost Tracking
Datasets
Alerts
Reports
HQL
Eval Scores
User Feedback

Prompt Management

Overview
Prompt Assembly
SDK Integration

Legacy Integrations

Overview

References

Model Provider Integration
PostHog
Cost Calculation
Data Security & Privacy
Header Directory
Latency
Open Source
Proxy vs Async
Reliability

FAQ - Using Helicone

Questions about how to best use Helicone’s platform features.

Incorrect cost calculation while streaming?

Learn how to accurately calculate costs when using streaming features.

Was this page helpful?

Suggest edits Raise issue

⌘I

twitter linkedin github discord

Powered byThis documentation is built and hosted on Mintlify, a developer documentation platform