OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Evaluation & Observability

Helicone

Helicone is an open-source LLM observability platform and AI gateway. It provides tools to inspect agent traces and sessions, track cost, latency and quality, iterate on prompts, and route requests to multiple AI models through one API with automatic fallbacks.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Helicone — OpenViST project profile in AI Evaluation & Observability.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Helicone when developing or operating LLM applications and you need request-level visibility, operational metrics, or a unified gateway for model calls.

Who it is for

  • AI engineers building applications that call language models.
  • Teams that need to inspect agent or chatbot traces and sessions.
  • Developers seeking a unified API for routing requests across AI models.

Documented uses

  • Inspect and debug LLM application traces and sessions.
  • Track request costs, latency and quality.
  • Route model requests through a gateway with automatic fallbacks.
  • Version prompts and test prompts, sessions and traces in a UI playground.
Before you choose

Requirements & limits

Helicone offers a hosted gateway workflow that requires a signup API key and credits. The project also documents self-hosting with Docker and Helm.

  • The platform combines observability with a gateway, but these serve distinct needs: logging and analysis versus routing model requests.
  • The repository documents integrations including OpenAI, Anthropic, LangChain, Gemini and Vercel AI SDK.
  • Self-hosting instructions recommend Docker or Helm; a production-ready Helm chart is available by contacting the project.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Send a model request through the Helicone AI Gateway

Configure the documented OpenAI JavaScript client example to send a request through Helicone's gateway.

Before you start

  • A Helicone API key obtained by signing up.
  • Credits added through the documented credits page.
  • The OpenAI JavaScript client.

Steps

  1. Set the client's baseURL to https://ai-gateway.helicone.ai.

  2. Set its apiKey to the HELICONE_API_KEY environment variable.

  3. Call chat.completions.create with a model and messages, following the repository example.

  4. View request logs in the Helicone dashboard.

Expected outcome

The example sends a chat-completions request through the gateway, with logs available in the dashboard.

Guide limitations

  • The steps document the gateway path, not self-hosted gateway setup.
  • The repository instructs users to add credits but does not specify an amount in the quick-start instructions.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
7 October 2026
Original website title
Helicone/helicone · Official homepage title · retained in its source language
How we review sourcesSuggest a correction