Claude Fable 5.2 API Pricing & Cost Breakdown
Deepest frontier reasoning, complex architectural planning, and high-stakes synthesis.
Input / 1M Tokens
$8.00
Cached Input / 1M
$0.200
Output / 1M Tokens
$40.00
Context Window
1M
Workload Cost Scenarios (30-Day Billing)
97.5% cached input read discount ($0.20/1M) on 1M context.
| Scenario | In / Out per Req | Uncached Monthly | 50% Cache Hit Monthly |
|---|---|---|---|
| Hobby / Prototype (100 req/day) | 1500 / 400 | $84.00 | $66.45 |
| Growing Startup (2,500 req/day) | 2500 / 700 | $3,600.00 | $2,868.75 |
| Production Scale (50,000 req/day) | 3000 / 800 | $84,000.00 | $66,450.00 |
Lower-Cost Alternative Models
Frequently Asked Questions
What is Claude Fable 5.2 API pricing per 1M tokens?
Standard input is $8.00/1M, cached input is $0.200/1M, and output is $40.00/1M.
What is the context window of Claude Fable 5.2?
Claude Fable 5.2 supports a 1M token context window with up to 128,000 max output tokens.
How much does prompt caching save on Claude Fable 5.2?
Prompt caching reduces cached input token rates by 98% compared with uncached input.
What workloads is Claude Fable 5.2 best suited for?
Deepest frontier reasoning, complex architectural planning, and high-stakes synthesis.