Short answerBoth providers bill per million tokens for input and output. The table shows a few published prices as of our check; the right model depends on quality needs, and prices change often, so use the providers' pricing pages for current numbers.
| Provider | Model (as listed) | Input / Output per 1M tokens |
|---|---|---|
| OpenAI | gpt-4o-mini | $0.15 / $0.60 |
| OpenAI | gpt-4.1 | $2.00 / $8.00 |
| OpenAI | gpt-5.5 | $5.00 / $30.00 |
| Anthropic | Claude Haiku 5.5 | $0.10 / $0.50 (prompts up to 100K tokens) |
| Anthropic | Claude Sonnet 5.5 | $2 / $10 |
| Anthropic | Claude Opus 5.5 | $4 / $20 |
Estimate your monthly cost
- Estimate tokens per question (instructions + retrieved file passages + question) and per answer.
- Multiply by questions per month.
- Apply the price for your chosen model.
Pasting the same long instructions and file passages into every request is usually the largest input. Use the calculator for totals. Costs overview: migration cost.
Check your GPT before you move it
Paste your instructions, file names and Actions schema into the free checker. It runs in your browser and builds a portable bundle. Nothing is uploaded.
Open the free checkerRelated guides
Sources
Pages describing other companies' products reflect their public documentation on the date shown and can go out of date.