Helicone OSS LLM Observability llms.txt · AI Docs Browser · mdream [llms.txt Tools](https://mdream.dev/llms-txt/helicone/llms-txt) # Helicone OSS LLM Observability llms.txt docs.helicone.ai/llms.txt [Raw llms.txt](https://docs.helicone.ai/llms.txt) [Raw llms-full.txt](https://docs.helicone.ai/llms-full.txt) Copy Markdown [](https://docs.helicone.ai/llms.txt) llms.txt Docs LLM Caching Custom Properties Custom LLM Rate Limits User Feedback LLM Security Moderations Prompt Assembly Prompt Management Overview SDK Integration Eval Scores Token Limit Exception Handlers User Metrics & Analytics Alerts Datasets HQL (Helicone Query Language) effortlessly deploy them across your app Editor Reports Sessions Webhooks Webhooks Local Testing Context Editing Error Handling & Fallback Image Generation Prompt Caching Reasoning Responses API Claude Agent SDK Integration OpenAI Codex DSPy LangChain Integration Langfuse Integration LangGraph Integration LiteLLM Integration LlamaIndex Integration n8n Integration OpenAI Agents Integration Integrations Overview PostHog Integration Semantic Kernel Integration Vercel AI SDK Integration Zapier Integration AI Gateway Overview Prompt Management Provider Routing Web Search Anyscale Integration Crew AI Integration Deepinfra Integration DeepSeek AI Integration Hyperbolic Integration LiteLLM Integration with Callbacks Manual Logger - cURL Manual Logger - Go Manual Logger - Python Manual Logger - TypeScript Mistral AI Integration Nebius Token Factory Integration Novita AI Integration OpenLLMetry Async Integration OpenRouter Integration Perplexity AI Integration PostHog Integration Together AI Integration Vercel AI SDK Integration Platform Overview Quickstart Docker Kubernetes Self-Hosting Self-Hosting Helicone Building and Monitoring AI Agents with Helicone Cost Tracking & Optimization Debugging LLM Applications Environment Tracking ETL / Data Extraction How to Run LLM Prompt Experiments How to fine-tune LLMs with Helicone and OpenPipe Retrieving Sessions Getting User Requests Integrating Helicone with GitHub Actions Helicone Evals with Ragas How to Label Your Request Data Manual Logger with Streaming Logging OpenAI Batch API Requests with Helicone How to build a chatbot with OpenAI structured outputs Predefined Request IDs How to Prompt Thinking Models Replaying LLM Sessions Using Custom Properties to Segment Data How to Build a Multi-Model AI Assistant with Vercel AI Gateway and Helicone Build an AI Debate Simulator with Vercel AI Gateway Helicone Guides Be specific and clear Implement few-shot learning Leverage role-playing Overview Use Chain-of-Thought prompting Use constrained outputs Use Least-to-Most prompting Use Meta-Prompting Use structured formats Use Thread-of-Thought prompting Helicone Header Directory Claude Code Anthropic cURL Integration Anthropic JavaScript SDK Integration Anthropic LangChain Integration Anthropic Python SDK Integration Azure OpenAI with cURL Azure OpenAI with JavaScript Azure OpenAI with LangChain Azure OpenAI with Python AWS Bedrock JavaScript SDK Integration AWS Bedrock Python SDK Integration Custom Logs with cURL Custom Logs with the Logger SDK Gemini AI cURL Integration Gemini JavaScript SDK Integration Gemini Python SDK Integration Vertex AI cURL Integration Vertex AI JavaScript SDK Integration Vertex AI Python SDK Integration Groq cURL Integration Groq JavaScript SDK Integration Groq Python SDK Integration Instructor JavaScript SDK Integration Instructor Python SDK Integration Llama cURL Integration Llama JavaScript SDK Llama Python SDK Nvidia NIM cURL Integration Nvidia Dynamo Integration Nvidia NIM JavaScript SDK Nvidia NIM Python SDK Ollama Javascript Integration OpenAI with cURL OpenAI JavaScript SDK OpenAI with LangChain OpenAI with LlamaIndex OpenAI Python SDK OpenAI Realtime API OpenAI Responses API Legacy Integrations Trace Tools with cURL Trace Tools with the Logger SDK Helicone MCP Server Xcode Integration (AI Gateway) Vector DB tracing with cURL Trace Any Vector DB interactions xAI cURL Integration xAI with OpenAI JavaScript SDK xAI with OpenAI Python SDK Dify LangGraph Integration Ragas Integration Availability and Reliability Data Security & Privacy How We Calculate Cost Latency Impact Open Source How to Integrate a Model Provider to the AI Gateway Proxy vs Async Integration Get Models Get Multimodal Models Chat Completions (Gateway) Responses (Gateway) Query Dashboard Scores Get Evaluation Scores Create Evaluation Query Evaluations Query Score Distributions Get Model Registry Delete Prompt Delete Prompt Version Get Prompt Count Get Environments Get Prompt Get Prompt Inputs Get Prompt Body Get Prompt Tags Update Prompt Tags Create Prompt Rename Prompt Query Prompts Get Prompt Version by Environment Get Production Version Get Prompt Version Counts Get Prompt Version Get Prompt Versions Update Prompt Set Version Environment Query Properties Get Single Request Get Request Inputs Submit Request Assets Submit Feedback Submit Score Get Requests (Point Queries) Get Requests Get Requests by IDs Upsert Request Property Add Session Feedback Query Session Metrics Query Sessions Log Trace Query User Metrics Overview Query User Metrics Get User Data Delete Webhook Get Webhooks Create Webhook OpenAPI Specs swagger ai-gateway.openapi ## What is Helicone OSS LLM Observability's llms.txt? Helicone OSS LLM Observability publishes an `/llms.txt` file that provides AI systems with a structured index of its documentation. It follows the [llms.txt specification](https://llmstxt.org), organizing links to guides, API references, and tutorials under section headings so that LLMs like ChatGPT, Claude, and Gemini can quickly understand what Helicone OSS LLM Observability offers and where to find details. Pass Spec 2 Sections 213 Links 37.7 KB Size ~9.7k Tokens Sections: Docs · OpenAPI Specs ## Add Helicone OSS LLM Observability Docs to Your AI Assistant Select your tool to see how to add Helicone OSS LLM Observability's llms.txt as a documentation source. Cursor Windsurf Claude Code ChatGPT Zed Copilot 1. 1 Open any chat or composer panel 2. 2 Type @Docs and select "Add new doc" 3. 3 Paste the URL: https://docs.helicone.ai/llms.txt 4. 4 Wait for the green dot (indexing complete) 5. 5 Reference @Docs in chat when asking about Helicone OSS LLM Observability Cursor crawls the URL and indexes all subpages. Add a trailing slash to index child pages too. ## Spec Compliance 5 notes ## Frequently Asked Questions Where is Helicone OSS LLM Observability's llms.txt file? Helicone OSS LLM Observability publishes its llms.txt at https://docs.helicone.ai/llms.txt. This file provides a structured, markdown-formatted index of Helicone OSS LLM Observability's documentation that AI systems can consume to understand the project's APIs, guides, and references. How do I use Helicone OSS LLM Observability's llms.txt with AI coding assistants? Copy the llms.txt content and paste it into your AI assistant (Cursor, Windsurf, Claude, ChatGPT) as context. This gives the AI an accurate map of Helicone OSS LLM Observability's documentation so it can provide better code suggestions and answers about Helicone OSS LLM Observability. What does Helicone OSS LLM Observability's llms.txt contain? Helicone OSS LLM Observability's llms.txt contains 2 sections and 213 documentation links in 37.7 KB (~9.7k tokens). Key sections include Docs, OpenAPI Specs. How many tokens does Helicone OSS LLM Observability's llms.txt use? The concise llms.txt index is approximately 9.7k tokens (37.7 KB). Most AI assistants can fit this within their context window. For the full expanded documentation, look for an llms-full.txt variant which embeds all content inline. Can I generate an llms.txt for my own project? Yes. Use the free llms.txt generator at mdream.dev/tools/llms-txt/generator to crawl your site and produce a spec-compliant llms.txt file. You can also validate existing files with the llms.txt validator. ## Browse More llms.txt Files [Labelbox](https://mdream.dev/llms-txt/helicone/llms-txt/labelbox) [Overview Build your design system in React, Solid, Vue or Svelte. Powered by finite state machines](https://mdream.dev/llms-txt/helicone/llms-txt/zag) [Activepieces](https://mdream.dev/llms-txt/helicone/llms-txt/activepieces) [Fiber](https://mdream.dev/llms-txt/helicone/llms-txt/gofiber) [Scanopy Documentation Network topology discovery and visualization platform. Scanopy helps you map your infrastructure by discovering hosts, services, and their relationships across your networks.](https://mdream.dev/llms-txt/helicone/llms-txt/scanopy) [HeroUI v3 Documentation A set of beautiful, customizable React and React Native components that stay maintained and up to date.](https://mdream.dev/llms-txt/helicone/llms-txt/heroui) [Kaneo](https://mdream.dev/llms-txt/helicone/llms-txt/kaneo) [smartcar](https://mdream.dev/llms-txt/helicone/llms-txt/smartcar) [View all 99 projects ](https://mdream.dev/llms-txt/helicone/llms-txt) ## Related Tools [

llms.txt Generator

Generate an llms.txt for your own project.](https://mdream.dev/llms-txt/helicone/tools/llms-txt/generator) [

llms.txt Validator

Validate your llms.txt against the official spec.](https://mdream.dev/llms-txt/helicone/tools/llms-txt/validator) © 2026 [Harlan Wilton](https://github.com/harlan-zw) · [MIT](https://github.com/harlan-zw/mdream/blob/main/license) [GitHub](https://github.com/harlan-zw/mdream) [Discord](https://discord.com/invite/275MBUBvgP)