The AI platforms I build on, and what each one did to me

Every page here covers a platform that my own code calls in a system I built and ran. Each one says what I made with it and what broke. Each gives the vendor's prices on the day I checked. If I have not shipped on a tool, it does not get a page.

Models

  • Claude is the primary model in my customer-facing chat assistants. The page includes the $50 billing limit that took every tenant offline in August 2026.
  • Groq serves open models faster than anything else I use. It ran my phone agent, and then it retired the model I built on.
  • OpenAI is third in line in my stack. Its request format is in half my code. Its models bill me almost nothing.

Voice and telephony

  • Twilio carried the calls. The page covers Media Streams wiring, numbers that keep billing after a customer leaves, and a texting registration that never cleared.
  • Deepgram did live speech-to-text. Includes the Safari bug that made a voice demo deaf.
  • Cartesia was the voice on the phone line and in my pitch videos, at about 1.8 cents per call minute.
  • Kokoro TTS is a free model on my Mac that now voices my narration. Five failure modes and the checks that catch them.

Data

  • Supabase holds logins and data for six of my apps. The page covers free-tier pausing and a login hang.

Comparisons

How one call uses five of these

The pages make more sense as a chain. On my AI receptionist, a single inbound call went through this path:

StepPlatformShare of a call minute
Phone number and live audio streamTwilio$0.0129
Caller's speech to textDeepgram$0.0048
Deciding what to sayA small open model on Groqabout $0.0006
Text to voiceCartesiaabout $0.018
Accounts and call recordsA database on my own server$0 marginal

That is about 3.6 cents a minute at November 14, 2026 list prices. The chat products swap the first four rows for a single Claude call and keep the last.

The rules for a page

  1. My code has to call it. I searched my own repositories and servers for each platform before writing. A job posting that mentions a tool does not count, and neither does an account I opened once.
  2. Prices come from the vendor's own page. Each page links the source and gives the date I read it. If I could not read a number, I left it out and said so.
  3. Failures stay in. The outage, the registration that never cleared, the key I pasted wrong. Those are the useful parts.
  4. Clients stay anonymous. I describe the business. I do not name it.

Platforms without a page, and why

n8n, Make and Zapier. I have not built a client system on any of them. My one contact with Make is a landing-page form I wired to post into a client's existing Make scenario. I write code on a server I control, for the reasons on the custom vs no-code page. A three-way comparison from me would be a rewrite of other people's reviews.

ElevenLabs. I designed one game announcer voice in its app by hand. No code of mine calls its API. Its published agent price appears on the voice comparison page, labeled as not run.

Google Gemini. It has been a fallback model in three of my apps and never a primary. That is too thin for a page.

When one of these moves into a system I run, it gets a page with dates on it.

Not sure which of these your business needs?

The free audit maps your operations and names the two or three places where one of these platforms would pay for itself. You get the answer whether or not you hire me.