# dillionverma/llm.report

📊 llm.report is an open-source logging and analytics platform for OpenAI: Log your ChatGPT API requests, analyze costs, and improve your prompts.

Repository: https://github.com/dillionverma/llm.report
Canonical: https://ross.abutalabs.com/products/llmreport
Homepage: https://llm.report
Language: TypeScript
License: GPL-3.0
License Family: copyleft
Topics: gpt-3, gpt-4, llm, llmops, openai, nextjs, open-source, nodejs, react, shadcn-ui, typescript, aiops, mlops
Archived: true
Last push: 2024-05-14T03:58:18+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 87
- inputs: {"age_days": 1226, "days_push": 841, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1020, forks 86 (observed 2026-08-28T04:03:15.258717+00:00)

## What it is
llm.report is an open-source logging and analytics platform for the OpenAI API, letting users log ChatGPT API requests and responses, analyze costs and token usage, and improve prompts. It is built with Next.js/TypeScript and can be self-hosted or used via cloud.

## Use cases
- track openai api costs
- log chatgpt api requests and responses
- analyze llm token usage
- improve prompts with request logs
- self-host llm observability dashboard
- monitor per-user llm api usage

## When to choose
- you need a self-hosted, no-code dashboard for OpenAI API costs and logs
- you want to inspect request/response payloads to refine prompts
- you prefer an open-source alternative to paid LLM observability tools

## When to avoid
- you need actively maintained software with ongoing fixes
- you use providers other than OpenAI
- you require enterprise-grade support or a sustainable vendor

## Facets
- artifact type: service
- maturity: abandoned
- function: logging, monitoring, analytics, llm-inference, prompt-engineering
- domain: large-language-models, analytics, monitoring, developer-tools, artificial-intelligence
- platform: self-hosted
- tags: openai, llmops, cost-tracking, token-usage, nextjs, observability, nodejs, web-server, docker

## Member repositories
- dillionverma/llm.report (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:15.258717+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:08:55.614364+00:00, confidence not recorded.
  - readme: https://github.com/dillionverma/llm.report (fetched 2026-08-28T04:03:15.258717+00:00, sha d1c6e180e33d)
- Data as of 2026-08-30T08:39:29.467469+00:00.