Helicone

AI gateway and LLM observability platform for logging, debugging and routing LLM requests

Observability tool by Helicone

IndexedApache-2.0★ 6,236

Write a review

Get started

Setup steps are in the repository. Website · Docs · Repository

About

Helicone sits in front of model providers as an OpenAI-compatible gateway, so one API key reaches 100+ models with automatic fallbacks. It logs requests, sessions, cost and latency, and offers prompt versioning, a playground and fine-tuning through partners. The project is open source and can be self-hosted with Docker.

Use cases: monitoring-observability, model-inference

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Category: Tracing · open source
Self-host: Yesraw.githubusercontent.com
Open source: Yesraw.githubusercontent.com
Compliance (vendor says): SOC 2, GDPRraw.githubusercontent.com
Works with: langchain, vercel-ai-sdkraw.githubusercontent.com
Protocols: openai-compatibleraw.githubusercontent.com

Plans

Hobby	$0	10,000 requests/mo, 7 day retention, 1 seat
Pro	$79/month	per month plus usage-based pricing; 1 month retention
Team	$799/month	per month plus usage-based pricing; 3 months retention; 5 organizations
Enterprise	Contact sales	contact us; unlimited retention, SAML SSO, customized MSAs

From the vendor's pricing page, read Oct 24, 2026.

Facts read from the vendor's own pages by claude-haiku-5-5 on Oct 24, 2026; a fact is shown only with the page it came from.

Signals

Stars: 6,236
Forks: 690
Open issues: 59
Last commit: Oct 20, 2026 (8 days ago)
Last release: Aug 21, 2025 (1 year ago)

From GitHub (fetched Oct 24, 2026).

Details

License: Apache-2.0
Repository: github.com/Helicone/helicone
Website: www.helicone.ai
Docs: docs.helicone.ai
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README Website Pricing page Docs github-graphql