Dopp

Dopp vs OpenAI fine-tuning

Dopp · 2026-09-24

OpenAI fine-tuning takes a JSONL file of examples and returns a customised version of one of their models, hosted by them. Dopp builds the examples from your live traffic, trains a small open model on them, measures it against that API, and lets you run it anywhere.


How is Dopp different?

The dataset builds itself. OpenAI's guide starts at "prepare your training file". Dopp starts at "change one URL". Every request your app sends is recorded with its answer, in your format, as you go.

Labels are included. With OpenAI you bring correct answers. With Dopp, Jev answers every request as it happens, and that answer is the label unless you pick another.

The model is yours. A fine-tuned OpenAI model lives on their servers, under their terms, at their price per token. An Dopp model is an open 0.4B model you can download, run on our GPU, or run in a browser tab.

Side by side

OpenAI fine-tuningDopp
Examples come fromA JSONL file you prepareYour live requests, plus paste, datasets, generated
Labels come fromYouJev, automatically; overridable
Base modelTheirs (closed)Open, small, downloadable
Where it runsTheir serversOur servers or the user's browser
Price to servePer token, fine-tuned rateCents per thousand on a small GPU, or free in the browser
Typed answersPrompted; you parseNative: choices, yes/no, scores with probabilities
MeasuringYour eval scriptHeld-out agreement per answer; live agreement on traffic
Fallback when unsureYou build itOne setting: ask Jev when unsure

When OpenAI fine-tuning is the better choice

When Dopp is the better choice

What OpenAI does better

Bigger models, more capable on hard or unusual inputs, and generation. If your "classification" secretly needs reasoning over long documents, their model will do better than a 0.4B one.

Pricing

OpenAI charges for training tokens and a higher per-token rate to serve the fine-tuned model. Dopp charges for Jev's labels (fractions of a cent), training minutes (cents to a dollar), and serving on a small GPU; the browser copy costs nothing to serve. Every price is shown before you press the button.

Switch in three steps

  1. Route your classification traffic through Dopp (one URL change; Jev answers meanwhile).
  2. Train when you have a few hundred requests.
  3. Compare against Jev on real traffic, then switch.

Questions

Can I export the model?

Yes: the weights, and the browser version.

Can I use my existing labelled data?

Yes: paste it in, or upload rows; each row becomes a request with your label as the grounded answer.

Does it handle many questions per request?

Yes, including one question per word of a text.

What about GPT-4-class accuracy?

Not the goal. The goal is Jev-level agreement on your own requests at a fraction of the cost, with Jev as the safety net.

What Dopp is. Dopp is a drop-in proxy for any Jev-compatible decision API: TypeSafe's Jev, Kev, GLiNER, simple-jev, or your own endpoint that answers typed questions about a state. You change one URL; every request still gets your current API's answer and is recorded as training data. When you have enough, one button trains a small open model on your own requests, measures it against the API it learned from on requests it never saw, and lets you choose who answers: the API, your model with the API as backup, or your model alone, on our servers, or offline, even in your users' browsers.