None
None
Long Story Video Skill
Turn your idea into 10s–10min video—AI writes scripts, prompts, and generates footage automatically.
Ads Video Skill
Generate professional ads and sales videos—AI auto-generates scripts, prompts, and footage.
3D Science Explainer Video Skill
Convert scientific concepts into stunning 3D explain animations
Feedback
freeTrialImage.bannerPity
freeTrialImage.upgradeUnlock
- ✓freeTrialImage.benefitHd
- ✓freeTrialImage.benefitWatermark
- ✓freeTrialImage.benefitUnlimited
claude fable
Claude Fable 5.2 handles tough reasoning and long agentic runs, pairing a 1M-token window with adaptive thinking you control by effort.
All Tools
Discover our comprehensive AI-powered animation toolkit
MiniMax H3
MiniMax H3 AI Video Generator
Seedance 2.5
The Future of AI Video Is Here.
Seedance 2.0
The Future of AI Video Is Here.
Seedance 2.0
The Future of AI Video Is Here.
Gemini Omni
Gemini Omni Video Generator
Image to Video
Generate videos from images
Gemini Omni 1.2 Flash
AI Multi-Scene Shorts Generator
Create viral AI Shorts instantly
What Makes Claude Fable 5.2 Worth Building On
As an upgrade for demanding reasoning and extended agentic work, Claude Fable 5.2 matches Claude Mythos 5.2 on the spec sheet.
- Engineered for Heavy Reasoning LoadsIf higher-effort evals on Claude Opus 5.5 still fall short, Claude Fable 5.2 is the next stop for demanding reasoning and long-running agentic work.
- 1M-Token Context, 128k OutputClaude Fable 5.2 and Claude Mythos 5.2 both accept up to one million tokens of context by default and at maximum, and each can output up to 128k tokens.
- Effort-Steered Adaptive ThinkingThinking cannot be disabled; the effort parameter instead controls its depth across low, medium, high, xhigh, and max, with high as the API default.
How to Move to Claude Fable 5.2
Choose your build path, prove the need with evals, then resolve breaking changes before production traffic moves.
Core Features of Claude Fable 5.2
On-demand compaction, mid-conversation tool changes, the computer use toolset, fast mode, strict tool use, and refusal handling all ship with Claude Fable 5.2.
On-Demand Compaction (Beta)
The compact-2026-09-04 beta header lets you decide when older turns are summarized, keeping your history append-only for the prefix check.
Tool Changes Mid-Conversation (Beta)
Rather than editing the tools array, add or remove tools in a system message; on the Claude API, Claude Platform on AWS, and Anthropic-managed Google Cloud, send the inline-tools-2026-09-15 header.
Computer Use Through the Toolset
Access computer use with the computer_toolset_20260801 toolset; declaring the older computer_20251124 tool now returns a 400 invalid_request_error, except on Amazon Bedrock.
Where Fast Mode Runs
Fast mode is available on the Claude API, on both Anthropic-managed and Google-managed Google Cloud, and in Claude in Microsoft Foundry as its own model, claude-fable-5-2-fast.
Strict Tool Use for Schema-Valid Output
For schema-valid JSON, keep tool_choice at auto and add strict: true or switch to JSON outputs; forced tool use errors out, and customer-managed encryption keys rule out structured outputs.
Refusal Handling, Fallback, and Billing
A refusal returns HTTP 200 with stop_reason refusal and a stop_details object; eligible categories can retry on Claude Opus 4.8 or Claude Opus 5, and fallback credit refunds the prompt-cache cost.
Claude Fable 5.2: Your Questions Answered
Answers to common questions about getting started with Claude Fable 5.2, migrating to it, and understanding its pricing.
Should I Begin With Claude Opus 5.5 or Claude Fable 5.2?
Begin on Claude Opus 5.5 for most workloads; move to Claude Fable 5.2 only after higher-effort evals on Opus still fall short of your needs.
Why Does Editing an Earlier Turn Return a 400 Error?
The prefix check inspects the system prompt, tools, and earlier messages before a thinking block, and any change fails the request. The thinking-binding-controls-2026-08-01 header with prefix_mismatch_behavior set to drop_block is a temporary workaround.
Which Models Can Read Claude Fable 5.2 Thinking Blocks?
Only Claude Fable 5.2 and Claude Mythos 5.2 can read each other's blocks. Anything the active model cannot read is dropped before delivery, and you are not billed for dropped blocks.
Can I Disable Thinking or Force a Specific Tool?
No. Sending thinking enabled with budget_tokens, or thinking disabled, both return 400, and so does tool_choice set to any or to a named tool. Effort levels and strict tool use are the supported routes.
How Does Claude Fable 5.2 Pricing Compare With Claude Fable 5.1?
Both input and output cost less than Claude Fable 5.1, which was $10 per million input and $50 per million output tokens. Cache reads remain 0.025 times base input, and batch runs cost $4 per million input tokens.
What Happens When a Request Is Refused?
You get HTTP 200 with stop_reason refusal plus a stop_details object naming the policy area. Some categories can retry through server-side fallback, and billing depends on the category.
Try Claude Fable 5.2 Before You Switch
Prove the need first: confirm whether Claude Opus 5.5 already meets your requirements, choose a build path, then test the four breaking changes on your own integration before production traffic moves to Claude Fable 5.2.