AI assistants and search decision

CheapChat

A competent technical user can replace CheapChat’s hosted UI and model-proxying by self-hosting an open-source conversational frontend (e.g., Chainlit or DocsGPT) wired to OpenAI APIs; you lose hosted billing/ops and multi-model convenience but not core capability.

Visit website
You pay

Not priced

No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.

You’d pay instead

$100one-off46 h to build

$45/mo6 h/mo upkeep

No published price to break even against.

Open-source builds that already do this

Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All CheapChat alternatives, with the arithmetic →

What a replacement has to do

  • User sends message → backend proxies to chosen LLM API → store conversation and tokens → render model response in chat UI.

What it still won’t have

  • Hosted access to many pre-integrated model endpoints (model catalogue shown on site)
  • Integrated billing and hosted account management
  • Operational reliability, SLAs and vendor-run safety/monitoring

What remains hard

  • Product polish and ongoing maintenance
Read the build prompt

First-year cost

No published price

CheapChat does not publish a price we could read, so there is nothing to compare against. What building costs is below.

Money you would actually spend

Keep paying
—

Subscription price × seats × 12

Build it
—

AI build —APIs + hosting —

Time you would spend

—

—

What you would spend

What we assumed

The verdict above measures whether you could build it. This one is only about money.

Runnable build prompt

Not run yet
Build a minimal, self-hosted AI chat app using Python (FastAPI) backend, Chainlit for conversational UI, Postgres for conversation storage, Redis for short-term session state, and Docker Compose for deployment. Core features in scope: user sign-in (email link or single-user mode), model selector (support at least OpenAI), send/stream messages to backend proxy, store messages and token usage in Postgres, basic usage tracking endpoint, and an admin page to view conversations and usage. Out of scope: multi-tenant billing gateways, analytics dashboards, and enterprise SSO. Include error handling for API failures, retries, rate-limit backoff, and unit/integration tests for the proxy and DB layer. Provide Docker Compose, README with setup steps, and a simple script to seed a demo conversation.
How we checked3 sources · 2/3 runs agreed · evidence score 60

How the score was reached

  • Partly verdict base52
  • An open-source build was found+5
  • 3 cited sources+3
  • Evidence score60

The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.

How scoring works →

Cited sources · 3

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

! 2 of 3 runs agreed; the verdict is the majority✓ Citations limited to fetched pages! 1 moat recorded