GPT-5.5 → Claude Fable 5.2: cost per request on six tasks
Claude Fable 5.2 costs 38–58% more than GPT-5.5 per request on six common tasks. It costs no more per result that works if its results work first time at least 38% more often than GPT-5.5's on translation, and 59% more often on search re-ranking.
List prices per million tokens
| Model | Input | Cached input | Output |
|---|---|---|---|
| GPT-5.5 | $5.00 | $0.50 | $30.00 |
| Claude Fable 5.2 | $8.00 | $0.20 | $40.00 |
Prices checked 2026-11-12.
Cost per 1,000 requests
| Task | GPT-5.5 | Claude Fable 5.2 | 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. | $24.00 | $36.00 | 50% more | 50% more often than GPT-5.5 |
| Invoice field extractionInstructions and one invoice's text in; about 15 fields as JSON out. | $20.00 | $30.00 | 50% more | 50% more often than GPT-5.5 |
| Lead scoringScoring rules and one lead's form answers in; a score and a one-line reason out. | $9.00 | $13.60 | 51% more | 52% more often than GPT-5.5 |
| Email reply draftInstructions and the email thread so far in; a reply of about 300 words out. | $19.50 | $28.00 | 44% more | 44% more often than GPT-5.5 |
| TranslationInstructions and about 500 words of text in; the same text in another language out. | $28.50 | $39.20 | 38% more | 38% more often than GPT-5.5 |
| Search re-rankingA search query and 20 result snippets in; the ids of the best five, in order, out. | $21.50 | $34.00 | 58% more | 59% more often than GPT-5.5 |
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.