| Item | Price per million tokens |
|---|---|
| Input | $8 |
| Output (incl. thinking) | $40 |
| Cache write, 5 minutes | $10 |
| Cache write, 1 hour | $16 |
| Cache read | $0.2 |
| Batch API input / output | $4 / $20 |
Model id: claude-fable-5-2
What it costs in practice
| Request | One request | 1,000 requests | One request, Batch API |
|---|---|---|---|
| Short chat reply 2,000 in / 300 out | $0.028 | $28.00 | $0.014 |
| Agent turn with tools and history 12,000 in / 800 out | $0.128 | $128.00 | $0.064 |
| Summarize a 40-page document 30,000 in / 1,000 out | $0.280 | $280.00 | $0.140 |
Prompt caching example
An agent sends the same 10,000-token system prompt and tool list on every call, plus 1,000 new tokens, and gets 500 tokens back. Over 20 calls inside a 5-minute cache window:
- Without caching: $2.16
- With caching (one cache write, then 19 cache reads): $0.698, about 68% less
Compared with other Claude models
- Claude Opus 5.5: $4 / $20, about 2× cheaper than Fable 5.2 for the same tokens.
- Claude Sonnet 5.5: $2 / $10, about 4× cheaper than Fable 5.2 for the same tokens.
- Claude Haiku 5.5: $0.1 / $0.5, about 80× cheaper than Fable 5.2 for the same tokens.
Side-by-side pages with worked examples:
Input + output price per million tokens, compared as a simple sum. Your real ratio depends on how many input versus output tokens your workload uses; the calculator compares models on your own numbers.
What a typical app costs on Claude Fable 5.2: chatbot, support bot, coding agent, document q&a (rag), document summarization, classification & extraction.
Questions
How much does Claude Fable 5.2 cost?
$8 per million input tokens and $40 per million output tokens. Prompt cache reads cost $0.2 per million tokens; cache writes cost $10 (5-minute) or $16 (1-hour) per million tokens.
What is the Claude Fable 5.2 model id?
Use "claude-fable-5-2" as the model parameter in the Messages API.
Is there a cheaper way to run Claude Fable 5.2?
Yes. Batch API requests cost 50% of the normal price, and prompt caching cuts the cost of repeated context. In the caching example on this page, 20 calls that share a 10,000-token prefix cost about 68% less with caching.