Anthropic

Claude Fable 5

Claude Fable 5 is a Claude 5 model from Anthropic, released in 2026-06. It costs $10 / $50 per 1M, has a 1M-token context window, and is best for hardest-coding, complex-reasoning, agents. Last verified 2026-06-11.

Spec sheet

Pricing

Input
$10 / 1M
Output
$50 / 1M
Cached input
$1 / 1M
Batch discount
50%
Free tier
No

Context & speed

Context window
1M tokens
Max output
128k tokens
Throughput
~50 tok/s
Time to first token
~1000 ms
Speed tier
slow

Capabilities

Tool use
Yes
Structured output
Yes
Prompt caching
Yes
Extended thinking
Yes
Vision input
Yes
Audio in / out
No
Fine-tuning
No

Deployment

Open weights
No
On-prem
No
HIPAA eligible
Yes
Zero retention
Yes
Regions
us, eu

Estimated monthly cost

Assumes typical token shape: 2k input, 600 output per call. Prompt caching is excluded from these figures.

10k calls/mo
$500.00
per month
100k calls/mo
$5.0k
per month
1M calls/mo
$50k
per month

When to use Claude Fable 5

Sweet spot

  • hardest coding
  • complex reasoning
  • agents
  • long horizon tasks
  • research

Known trade-offs

  • 2x Opus pricing
  • safety classifiers can decline edge-case requests
  • overkill for routine tasks

Works with

Anthropic SDKClaude CodeCursorAWS BedrockGoogle Vertex AIVercel AI SDKLangChainLlamaIndexOpenRouter

FAQ — Claude Fable 5

How much does Claude Fable 5 cost?

Claude Fable 5 costs $10 / $50 per 1M tokens on the Anthropic API. Cached input reads cost $1 per 1M, cutting the input bill by roughly 90% on repeat system prompts. The batch API offers a 50% discount for async workloads.

What is the context window of Claude Fable 5?

Claude Fable 5 has a 1M-token context window with up to 128k tokens of output. That's enough for entire codebases, long transcripts, or multi-document RAG.

Does Claude Fable 5 have a free tier?

No — No free API tier; available via Claude.ai paid plans.

Is Claude Fable 5 HIPAA / EU / on-prem friendly?

Claude Fable 5 is HIPAA-eligible, available in EU regions, and is API-only. Zero data retention is available for enterprise customers.

What is Claude Fable 5 best for?

Claude Fable 5 is best for hardest coding, complex reasoning, agents, long horizon tasks. Trade-offs to be aware of: 2x Opus pricing; safety classifiers can decline edge-case requests; overkill for routine tasks.

Which tools and SDKs work with Claude Fable 5?

Claude Fable 5 integrates with Anthropic SDK, Claude Code, Cursor, AWS Bedrock, Google Vertex AI, Vercel AI SDK, LangChain, LlamaIndex, OpenRouter. Most major AI frameworks support it either natively or through OpenAI-compatible endpoints.