Next generation intelligence for long-running autonomous agents
| Scenario | Input Tokens | Output Tokens | Uncached Cost | With Prompt Caching |
|---|---|---|---|---|
| Short Chat Query | 1,000 | 500 | $0.0350 | $0.0253 |
| Document Summarization | 10,000 | 2,000 | $0.2000 | $0.1025 |
| Codebase & Context Analysis | 100,000 | 20,000 | $2.00 | $1.025 |
| Batch Corpus Processing | 1,000,000 | 100,000 | $15.00 | $5.25 |
Ideal for production workloads demanding reasoning capabilities, deep context depth (200k tokens), and reliability from Anthropic. Excellent when predictable tokenomics and prompt caching support are paramount.
If your use-case requires sub-second streaming latency or ultra-high frequency classification at micro-cent pricing, consider lighter budget options such as Gemini Flash-Lite or Claude Haiku. For deep formal logic, consider dedicated reasoning models like o3.
For Claude Fable 5.1, 1 million input tokens costs $10.00, while 1 million output tokens costs $50.00. If using prompt caching, repetitive input prefixes are discounted to $0.25 per million.
Claude Fable 5.1 features a maximum context window of 200,000 tokens (~150,000 words), with a maximum output limit of 32,768 tokens per completion.
Claude Fable 5.1 utilizes the Anthropic Claude BPE (~65k vocabulary). Token counting on TokenMath runs client-side to ensure maximum privacy.
Yes. Claude Fable 5.1 supports prompt caching with a cached input rate of $0.25/1M (saving up to 98% on repeated input context).