Self-hosted and open source - verified
Helicone (open source)
Helicone is listed under self-hosted and open source. Its first listed fee, in its own words: open source (Apache 2.0), self-hosted software. It states OpenAI-compatible requests. Routing stated: fallbacks. Read from the vendor's own pages on October 18, 2026.
Read from github.com, raw.githubusercontent.com. Docs - Compare every gateway
Status
- Status, as we read it
maintained repository (no archive notice in checked README)inferred
Our reading: The page implies this status without labelling it.
“Generous monthly free tier (10k requests/month) - No credit card required!”
raw.githubusercontent.com
How Helicone charges
Every fee line Helicone states, in its own words and units, with the quote. Nothing is converted.
| Product | Fee, in the vendor's words | Applies to | Quote and source |
|---|---|---|---|
| Helicone (open source) | open source (Apache 2.0) | self-hosted software | “Apache License” |
Access and keys
- Free tier
- Not stated
Open-source software; free tier not applicable.
- Bring your own key
- Not stated
Not stated for self-hosted deployments in the checked README.
- BYOK fee
- Not stated
Not applicable.
API formats
- OpenAI-compatible
yes (AI Gateway through the OpenAI API)
“Access 100+ AI models with 1 API key through the OpenAI API with intelligent routing and automatic fallbacks.”
raw.githubusercontent.com - Anthropic-compatible
- Not stated
Not stated in the checked README.
- OpenAI base URL
- Not stated
Self-hosted; base URL depends on deployment.
- Anthropic base URL
- Not stated
Not stated in the checked README.
Routing
- Fallbacks
yes
“intelligent routing and automatic fallbacks”
raw.githubusercontent.com - Load balancing
- Not stated
Not stated in the checked README.
- Automatic model routing
- Not stated
Not stated in the checked README.
Caching
- Exact-match cache
- Not stated
Not stated in the checked README.
- Semantic cache
- Not stated
Not stated in the checked README.
Controls and observability
- Spend controls
- Not stated
Not stated in the checked README.
- Rate limits
- Not stated
Not stated in the checked README.
- Guardrails
- Not stated
Not stated in the checked README.
- Observability
LLM observability platform
“Helicone is an AI Gateway & LLM Observability Platform for AI Engineers”
raw.githubusercontent.com - Telemetry and log export
- Not stated
Not stated in the checked README.
Data, deployment and license
- Data logging and retention
- Not stated
Self-hosted; not stated.
- Regions
- Not stated
Self-hosted; not applicable.
- Self-hosting
yes (Docker Compose; Helm chart for enterprise on request)
“Helicone is simple to self-host and update.”
raw.githubusercontent.com - License
Apache 2.0
“Version 2.0, January 2004”
raw.githubusercontent.com
Vendor-stated counts
Model and provider counts as Helicone states them, dated. When two pages disagree, both are shown.
100+ AI models (README) (vendor-stated, Oct 18 2026)
“Access 100+ AI models with 1 API key”
raw.githubusercontent.com
Research notes
The README says 100+ AI models while the hosted docs say 100+ LLM providers; both recorded as stated.
FAQ
How much does Helicone cost?
In Helicone's own terms: open source (Apache 2.0) (self-hosted software). As of October 18, 2026; fees are not converted.
Does Helicone support bring your own key?
Not stated. Not stated for self-hosted deployments in the checked README.
Is Helicone OpenAI-compatible or Anthropic-compatible?
OpenAI: yes (AI Gateway through the OpenAI API). Anthropic: not stated. Not stated in the checked README.
Sources
Last verified from each vendor's own docs, pricing pages, READMEs and license files; every quote was string-matched against the page that day. Fees are shown in the vendor's own words and change without notice, so check the linked source before you commit.
Newsletter
Know when a gateway changes its fees
One email per week. New model releases, routing and pricing changes and what they mean for what you build.