anthropic/claude-fable-5.2/chatAnthropic's Claude Fable 5.2 API brings 1,000,000-token context, 128,000-token output, five adaptive thinking effort tiers, and lower token pricing than Fable 5.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- Input types
- Text
- Output types
- Text
- Input
- $7.20 / 1 million tokens
- Cached input
- $0.72 / 1 million tokens
- Output
- $36 / 1 million tokens
- Context
- 1M
- Max output
- 128K
$7.20/36per 1 million tokens · input / output
late-night-scene-continuation Demonstrates medium-effort literary drafting in a candlelit Parisian study, maintaining slow-burn romantic tension, wardrobe continuity, and crisp dialogue between two adults in their thirties.
- 1200
- medium
- Input types
- Text
- Output types
- Text
- Input
- $7.20 / 1 million tokens
- Cached input
- $0.72 / 1 million tokens
- Output
- $36 / 1 million tokens
- Context
- 1M
- Max output
- 128K
$7.20/36per 1 million tokens · input / output
deep-architecture-review Uses high reasoning_effort to audit a three-service ledger migration for lock contention, outbox replay idempotency, and phased zero-downtime rollback gates.
- 2400
- high
- Input types
- Text
- Output types
- Text
- Input
- $7.20 / 1 million tokens
- Cached input
- $0.72 / 1 million tokens
- Output
- $36 / 1 million tokens
- Context
- 1M
- Max output
- 128K
$7.20/36per 1 million tokens · input / output
max-effort-debug-plan Engages max reasoning_effort to reconstruct a concurrent webhook retry race condition, specify a minimal transactional guard, and design a deterministic concurrency test.
- 3200
- max
This example starts at Input $7.20 / Output $36 per 1 million tokens. The Playground updates the estimate when you change the settings.
