Helicone LLM Observability Gateway

Helicone is an open-source LLM observability platform that logs requests with cost, latency, tokens and full prompts and responses. This template deploys the self-hosted stack (release v2025.08.21) with ClickHouse, Postgres and S3-compatible storage.

What you get

  • Caddy router on one public domain with path routing
  • Helicone dashboard and Jawn API server, which also proxies OpenAI and Anthropic calls
  • ClickHouse for analytics and Postgres for accounts and API keys, both on volumes
  • SeaweedFS for request and response bodies
  • Admin account created automatically; public sign-up closed

Good for

  • Logging LLM calls with cost, latency and token usage
  • Debugging agents with sessions and full request bodies
  • Tracking spend across OpenAI and Anthropic
  • Keeping prompts and completions inside your own project

Services in this template

  • web · image helicone/web:v2025.08.21
  • clickhouse · from baranberkay96/helicone-railway
  • proxy · from baranberkay96/helicone-railway
  • jawn · image helicone/jawn:v2025.08.21
  • Postgres · image ghcr.io/railwayapp-templates/postgres-ssl:17
  • seaweedfs · from baranberkay96/helicone-railway
  • migrations · from baranberkay96/helicone-railway

Questions people ask

How do I log in?

Enter your email in HELICONE_ADMIN_EMAIL at deploy. When the migrations service logs that it finished, open /signin on the proxy domain and use that email with HELICONE_ADMIN_PASSWORD from the migrations service variables.

How do I send traffic through it?

Create a Helicone API key in Settings. Point OpenAI clients at https://{proxy-domain}/jawn/v1/gateway/oai/v1, or Anthropic clients at /jawn/v1/gateway/anthropic, with a Helicone-Auth Bearer header. Your provider key stays in your app.

How do I add teammates?

Public sign-up is closed. Set HELICONE_ALLOW_SIGNUP to true on the proxy service while teammates register, then switch it back. Emails need SMTP, which requires a Railway Pro plan.

How do I upgrade?

Upgrade the web, jawn and migrations images together to a newer release tag and redeploy. The migrations job applies schema changes. ClickHouse is pinned in services/clickhouse/Dockerfile.

What are the scaling limits?

jawn and web are stateless and can run more replicas. ClickHouse and Postgres scale vertically.

Full template README

Deploy and Host Helicone with Railway

Helicone is an open-source LLM observability platform. Point your OpenAI or Anthropic client at Helicone's proxy and every request is logged with cost, latency, tokens and the full prompt and response. This community template deploys Helicone's self-hosted stack on Railway with ClickHouse, Postgres and S3 storage, and creates your admin account automatically.

About Hosting Helicone

Self-hosted Helicone consists of a Next.js dashboard, the Jawn API server (which also proxies LLM calls), Postgres for accounts, organizations and API keys, ClickHouse for request analytics, and S3-compatible storage for request and response bodies. Helicone's own Docker guide runs everything in one container and has you fix the first account with SQL. This template splits the services the way Helicone's Helm chart does, puts them behind one HTTPS domain with path routing, runs the database migrations as a job, creates a verified admin account and organization, closes public sign-up, and generates every secret, so you can log in and send your first request a few minutes after deploying.

Common Use Cases

  • Log every LLM call from your apps with cost, latency and token usage per user, feature or custom property.
  • Debug agents and multi-step chains with sessions and the full request and response bodies.
  • Track spend across OpenAI and Anthropic and set alerts on errors or cost.
  • Keep prompts and completions inside your own infrastructure for privacy or compliance.
  • Query your LLM traffic with HQL (SQL over your logs) and export datasets.

Dependencies for Helicone Hosting

  • Helicone images helicone/web, helicone/jawn and helicone/migrations, release v2025.08.21
  • ClickHouse 24.3
  • PostgreSQL 17 (Railway Postgres)
  • SeaweedFS (S3-compatible storage)
  • Caddy (router on the public domain)

Deployment Dependencies

Implementation Details

Service Role Public Storage
proxy Caddy router: /jawn/* to Jawn, bucket paths to SeaweedFS, rest to the dashboard; sign-up gate Yes –
web Helicone dashboard (Next.js, Better Auth) No –
jawn API server and LLM proxy (/jawn/v1/gateway/oai/v1, /jawn/v1/gateway/anthropic) No (via proxy) –
migrations One-shot job: database migrations and first admin account No –
clickhouse Request analytics No Volume
Postgres Accounts, organizations, API keys, prompts No Volume
seaweedfs Request and response bodies No (presigned via proxy) Volume

First login

  1. Enter your email in HELICONE_ADMIN_EMAIL when deploying (the only required input).
  2. Wait until migrations has finished (its logs end with migrations and bootstrap finished).
  3. Open https://{your-proxy-domain}/signin and sign in with that email and the generated HELICONE_ADMIN_PASSWORD from the migrations service variables.
  4. Create a Helicone API key in Settings, then point your client at the proxy:
    • OpenAI: base URL https://{your-proxy-domain}/jawn/v1/gateway/oai/v1, header Helicone-Auth: Bearer {your-helicone-key}
    • Anthropic: base URL https://{your-proxy-domain}/jawn/v1/gateway/anthropic, same header

Your provider API key stays in your app and is passed through to the provider.

Teammates: public sign-up is closed. Set HELICONE_ALLOW_SIGNUP=true on proxy while teammates create accounts, then switch it back. Verification and invite emails need SMTP settings on web (outbound SMTP requires a Railway Pro plan).

Scaling: jawn and web are stateless and can run more replicas; Jawn carries the proxied LLM traffic. ClickHouse scales vertically.

Pinning and upgrades: web, jawn and migrations are pinned to Helicone's release tag v2025.08.21 (the latest published images, also used by Helicone's Helm chart). Upgrade all three together to a newer release tag and redeploy; migrations applies new schema changes. ClickHouse is pinned in services/clickhouse/Dockerfile.

Resources: about 1.6 GB RAM idle (around $19/month); a team logging up to a million requests a month typically uses about 3.5 GB (around $50/month). Hobby plan works; Pro helps once stored bodies grow past 5 GB.

Why Deploy Helicone on Railway?

Railway runs the dashboard, API, databases and storage as one project with private networking, volumes, generated secrets and usage-based billing. You get a self-hosted LLM observability stack on your own domain without managing servers, and your prompts and completions never leave your project.

Guides for this template

View Helicone LLM Observability Gateway on railway.com

Similar templates

TemplateCategoryDeploymentsDeploys
9Router
Self-hosted AI router for Claude, Gemini, Cursor & OpenAI tools.
AI/ML9,734
flowise-railway
Flowise - low-code LLM apps builder
AI/ML8,512
LibreChat
Open-source ChatGPT clone: multi-model, agents, search, multi-user auth
AI/ML6,762
Hermes Agent by Nous Research
Template for Hermes Agent by Nous Research
AI/ML6,413
OpenClaw
[Homebrew support] The AI that actually does things
AI/ML5,167
Hermes Agent
Self Host Hermes Agent. Autonomous AI agent w/ self-improving, tools & more
AI/ML4,092