Applications
Fine-tuning cost calculator
Training cost of a supervised fine-tune from examples, tokens per example and epochs, on OpenAI's published training prices.
Prices read from the vendor pages on 2026-10-20. Arithmetic on list prices, not advice or a quote.
Saving and exports need Norwell Tools Pro, $9 a month. See what is in it. Everything above is free.
How it works
Training is billed per token actually trained, so epochs multiply the bill. Inference on a fine-tuned model is priced separately on the vendor page and is not included here.
The formula
training_tokens = examples * avg_tokens * epochs; cost = training_tokens * training_price / 1,000,000Worked example
With the inputs the page opens on:
- base model: gpt-4.1-mini-2025-04-14
- examples: 5000
- avg tokens per example: 600 tokens
- epochs: 3
gives
- training tokens: 9,000,000 tokens
- training cost: $45
- cost per epoch: $15
Sources
- https://developers.openai.com/api/docs/pricing (read 2026-10-20)
Prices read from each vendor's own pricing page on 2026-10-20; the page may have changed since. This is arithmetic on published list prices, not advice or a quote. Check the vendor's page before committing a budget.
Questions
Why only OpenAI?
Related tools
Monthly cost of a chat assistant where every turn re-sends the conversation so far.
Monthly cost of a retrieval-augmented answer flow: query embedding, retrieved chunks in the prompt, and the generated answer.
Cost of an agent loop where each step re-reads the growing transcript: steps, tool results and output per step.
AI cost per active user a month, gross margin at your price, and the break-even price for an AI feature.