Claude Fable 5.2 → GPT-5.5: cost per request on six tasks
GPT-5.5 costs 27–37% less than Claude Fable 5.2 per request on six common tasks. It costs no more per result that works if its results work first time at least 64% as often as Claude Fable 5.2's on search re-ranking, and 73% as often on translation.
List prices per million tokens
| Model | Input | Cached input | Output |
|---|---|---|---|
| Claude Fable 5.2 | $8.00 | $0.20 | $40.00 |
| GPT-5.5 | $5.00 | $0.50 | $30.00 |
Prices checked 2026-11-12.
Cost per 1,000 requests
| Task | Claude Fable 5.2 | GPT-5.5 | Change | Cheaper per result that works if it works first time at least |
|---|---|---|---|---|
| Support bot answerInstructions, three help-centre passages and the customer's question in; a short answer out. | $36.00 | $24.00 | 33% less | 67% as often as Claude Fable 5.2 |
| Invoice field extractionInstructions and one invoice's text in; about 15 fields as JSON out. | $30.00 | $20.00 | 33% less | 67% as often as Claude Fable 5.2 |
| Lead scoringScoring rules and one lead's form answers in; a score and a one-line reason out. | $13.60 | $9.00 | 34% less | 67% as often as Claude Fable 5.2 |
| Email reply draftInstructions and the email thread so far in; a reply of about 300 words out. | $28.00 | $19.50 | 30% less | 70% as often as Claude Fable 5.2 |
| TranslationInstructions and about 500 words of text in; the same text in another language out. | $39.20 | $28.50 | 27% less | 73% as often as Claude Fable 5.2 |
| Search re-rankingA search query and 20 result snippets in; the ids of the best five, in order, out. | $34.00 | $21.50 | 37% less | 64% as often as Claude Fable 5.2 |
Token counts are typical sizes, not measurements.
Test it on your own prompt
The model switch test runs your prompt on both models side by side with your own API key, in your browser.