Evals & observability
Helicone
One-line proxy that logs every request with cost and latency attribution per user or feature.
- Category
- Evals & observability
- Pricing
- Free tier
- Runs
- Hosted or self-hosted
- Interface
- Proxy, SDK, Dashboard
- Source
- Open source
What Helicone is
Helicone works as a proxy: change your base URL and every request is logged, with no instrumentation in application code. That makes it the fastest way to answer "what are we actually spending, and on what" — add custom properties for user, feature, or tenant and cost aggregates by whichever dimension you care about.
Best for
Getting cost and latency visibility across a codebase quickly, especially one you do not want to instrument.
Consider something else if
Proxy-level capture sees requests and responses but not the structure inside your application; deep agent traces want an SDK.
Helicone alternatives
The closest options in evals & observability, on the axes that actually separate them.
| Tool | Best for | Pricing | Runs |
|---|---|---|---|
| Heliconeopen source | Getting cost and latency visibility across a codebase quickly, especially one you do not want to instrument. | Free tier | Hosted or self-hosted |
| Langfuseopen source | Teams who need traces containing customer data to stay inside their own infrastructure. | Open source | Hosted or self-hosted |
| Portkeyopen source | Teams that want routing and request-level tracing from one system instead of integrating a gateway and an observability tool separately. | Free tier | Hosted or self-hosted |
| LangSmith | LangChain and LangGraph users, who get the deepest integration for the least work. | Free tier | Hosted |
| Braintrust | Teams treating prompt changes as changes that need tests, with evals wired into CI. | Free tier | Hosted |
| Phoenixopen source | Teams standardised on OpenTelemetry, and anyone debugging retrieval quality interactively. | Open source | Hosted or self-hosted |
Choosing within evals & observability
Tracing or evaluation first
Some tools lead with tracing and add evals; others are eval-first with tracing attached. If you are debugging today, start with tracing. If you are about to change a prompt that is already in production, start with evals.
How it gets your data
A proxy needs a one-line base-URL change and captures everything. An SDK needs instrumentation and captures more structure. OpenTelemetry-based tools slot into tracing you may already run.
Questions
What is Helicone?
Helicone works as a proxy: change your base URL and every request is logged, with no instrumentation in application code. That makes it the fastest way to answer "what are we actually spending, and on what" — add custom properties for user, feature, or tenant and cost aggregates by whichever dimension you care about. It is open source and hosted or self-hosted.
What are the alternatives to Helicone?
The closest alternatives are Langfuse, Portkey, LangSmith, Braintrust, Phoenix. They sit in the same category — evals & observability — and differ mainly on hosting model, pricing shape, and how much they abstract away.
Is Helicone the right choice?
Getting cost and latency visibility across a codebase quickly, especially one you do not want to instrument. The main caveat: Proxy-level capture sees requests and responses but not the structure inside your application; deep agent traces want an SDK.
Whatever you build on, the model is the line item that scales. See what each one costs per million tokens, or price your own workload.