Helicone
An open-source AI gateway and LLM observability platform: routing, fallbacks, tracing and cost tracking.
Sources and review
Checked against public documentation on . Suitability guidance is our editorial judgment; this is not a performance benchmark or an endorsement.
Adding cost, latency and trace visibility to an LLM app with minimal code changes.
About Helicone
Helicone combines an AI gateway, which reaches more than 100 models through the OpenAI API with routing and automatic fallbacks, with an observability platform that logs requests from OpenAI, Anthropic, LangChain, Gemini and the Vercel AI SDK in one line of code. It traces agent sessions, tracks cost and latency, offers a prompt playground and datasets, and can be self-hosted or used in the cloud.
Helicone is listed in this index written primarily in TypeScript, with 6.3k stars on GitHub. Its latest recorded repository push was in October 2026; that is not an ASE editorial review date.
Helicone and related category tools
Alternatives guide →| Record | Stars | Pricing | ||
|---|---|---|---|---|
| Heliconethis listing | 6.3k | TypeScript | Apache-2.0 | Costs not checked |
| LangSmith | — | — | — | Developer tracing allowance; paid seats, usage and separate service entitlements |
| Langfuse | 37k | TypeScript | MIT | Costs not checked |
| Arize Phoenix | 12k | Python | Elastic-2.0 | Self-host software; infrastructure and evaluator/model costs |
| Opik | 23k | Python | Apache-2.0 | Costs not checked |
| gateway | 13k | TypeScript | MIT | Costs not checked |
