Claude Fable 5.2 API price, and what each result really costs
Anthropic, listed 9 Nov 2026. Price checked 12 Nov 2026; unchanged since we started tracking it. Source: Anthropic's pricing page. anthropic/claude-fable-5.2
List price per million tokens
- Input
- $8.00
- Cached input
- $0.20
- Output
- $40.00
- Context window
- 1M tokens
Note: Added automatically on 2026-11-12: OpenRouter and LiteLLM (claude-fable-5-2) listed the same price.
What it costs per task, and per task that works
Six common task shapes with typical token counts. The real cost counts the tries that get redone; the rates are examples, not measurements.
| Task | Per 1,000 tries | Per 1,000 that work, 8 in 10 | Per 1,000 that work, 6 in 10 | Per 1,000 that work, 4 in 10 |
|---|---|---|---|---|
| Support bot answer3,000 in / 300 out | $36.00 | $45.00 | $60.00 | $90.00 |
| Invoice field extraction2,500 in / 250 out | $30.00 | $37.50 | $50.00 | $75.00 |
| Lead scoring1,200 in / 100 out | $13.60 | $17.00 | $22.67 | $34.00 |
| Email reply draft1,500 in / 400 out | $28.00 | $35.00 | $46.67 | $70.00 |
| Translation900 in / 800 out | $39.20 | $49.00 | $65.33 | $98.00 |
| Search re-ranking4,000 in / 50 out | $34.00 | $42.50 | $56.67 | $85.00 |
Work out your own real cost per resultTest Claude Fable 5.2 on your own prompt
Compare Claude Fable 5.2 with
- Claude Fable 5.1$10.00 in / $50.00 outSwitch cost
- Claude Opus 5$5.00 in / $25.00 outSwitch cost
- GPT-6 Astra$10.00 in / $50.00 outSwitch cost
- GPT-5.5$5.00 in / $30.00 outSwitch cost
- GPT-5.6 Sol$4.00 in / $20.00 outSwitch cost
Questions
How much does the Claude Fable 5.2 API cost?
$8.00 per million input tokens and $40.00 per million output tokens, or $0.20 per million for cached input. Price checked 12 Nov 2026; unchanged since we started tracking it.
What does a result that works really cost with Claude Fable 5.2?
A support bot answer (about 3,000 tokens in, 300 out) costs $0.036 per try. If 6 in 10 work first time, each answer that works really costs $0.06, because the redone ones were paid for too.