What it is

Open-source LLM observability that works as a one-line proxy: change your base URL and every request is logged with cost, latency and prompt content. It adds caching, rate limiting and per-user spend tracking, with an async SDK if you would rather not proxy.

Why it earns a slot

The lowest-effort way to find out where your token spend actually goes — no instrumentation, no framework buy-in, just a base URL swap. Per-user cost tracking is what makes usage-based billing possible.

Know before you commit

Proxy mode puts a third party in your critical path, adding latency and an outage dependency — use the async logger in production, or self-host. Free retention is only 7 days.

Getting started

npm i @helicone/helpers

Field notes

0 from the community

Sign in to add a field note. Reading is always open.

Loading notes…

Field check

Unverified

Sign in to confirm this entry is still accurate.

Pricing snapshot

Hobby free (10,000 requests, 1GB, 7-day retention), Pro $79/mo, Team $799/mo, Enterprise custom, all usage-based above included requests. Open source and self-hostable; 50% startup discount.

Snapshots move fast — verify at checkout, and post a field note if it changed.

Drop into your Lovable chat

Evaluate Helicone (https://www.helicone.ai) for this project, then use it only if it fits what we are already building.
Context: LLM observability proxy. Open-source LLM observability that works as a one-line proxy: change your base URL and every request is logged with cost, latency and prompt content. It adds caching, rate limiting and per-user spend tracking, with an async SDK if you would rather not proxy.
Reviewer notes (general, not written for this codebase): The lowest-effort way to find out where your token spend actually goes — no instrumentation, no framework buy-in, just a base URL swap. Per-user cost tracking is what makes usage-based billing possible.
Watch out for: Proxy mode puts a third party in your critical path, adding latency and an outage dependency — use the async logger in production, or self-host. Free retention is only 7 days.
Pricing: Hobby free (10,000 requests, 1GB, 7-day retention), Pro $79/mo, Team $799/mo, Enterprise custom, all usage-based above included requests. Open source and self-hostable; 50% startup discount.
Setup: npm i @helicone/helpers
Rules: treat the notes above as background only. Do not assume a theme, style, layout or feature that is not already in this project — inspect the existing code first and ask me before changing visual direction.

/api/public/tools/helicone

Also in Model APIs, routers & observability

Anthropic API / Claude Platform

platform.claude.com

Frontier model provider API

PaidModel APIs, routers & observability

Per token. Opus 5 $5/$25 per M in/out; Sonnet 5 $2/$10; Haiku 4.5 $1/$5; Fable 5 and Mythos 5 $10/$50. Batch API 50% off; cache reads 0.1x input.

Open dossier

Braintrust

braintrust.dev

LLM eval and experiment platform

Free tier + paidModel APIs, routers & observability

Starter free ($10/mo model credits, 1GB data, 10k scores, 14-day retention), Pro $249/mo ($249 credits, 5GB, 50k scores), Enterprise custom. Overage $3-4/GB and $1.50-$2.50 per 1k scores.

Open dossier

Fal.ai

fal.ai

Generative media inference host

PaidModel APIs, routers & observability

Per output or per second for media models: images ~$0.02-$0.04 at 1MP, video $0.05-$0.40 per second. Serverless GPU rates $1.10-$8.50/hr with committed-use discounts.

Open dossier

Fireworks AI

fireworks.ai

Open-model inference host

Free tier + paidModel APIs, routers & observability

Per token serverless across Standard/Priority/Fast tiers; embeddings $0.008-$0.10/M. On-demand GPUs billed per second: H100/H200 ~$7-8/hr, B200 ~$10-13/hr. Fine-tuning $0.50-$40 per M training tokens. $1 free credit.

Open dossier