Claude Fable 5 vs Claude Sonnet 4.6
Detailed comparison of API pricing, technical specifications, and benchmark scores. Updated 2026-06-29.
Cost at a Glance
Claude Fable 5 is 3.3× more expensive than Claude Sonnet 4.6 — switching could save 70% on your monthly API bill.
At 5M input + 2M output tokens per month:
Choosing Claude Sonnet 4.6 could save you $105.00/mo
Price Comparison (per 1M tokens)
| Metric | Claude Fable 5 | Claude Sonnet 4.6 |
|---|---|---|
| Input (per 1M tokens) | $10.00 | $3.00 |
| Output (per 1M tokens) | $50.00 | $15.00 |
| Cache Write (per 1M tokens) | $12.50 | $3.75 |
| Cache Read (per 1M tokens) | $1.00 | $0.30 |
| Batch Input (per 1M tokens) | $5.00 | $1.50 |
| Batch Output (per 1M tokens) | $25.00 | $7.50 |
Prices are per 1 million tokens. Actual costs depend on your monthly token volume. Use the calculator →
Specifications
| Spec | Claude Fable 5 | Claude Sonnet 4.6 |
|---|---|---|
| Context Window | 1M | 1M |
| Max Output Tokens | 128K | 128K |
| Knowledge Cutoff | 2026-04 | 2026-03 |
| Modalities | Text, Image | Text, Image |
| Prompt Caching | Yes | Yes |
| Batch API | Yes | Yes |
| Thinking / Reasoning | Yes | Yes |
Benchmark Scores
| Benchmark | Claude Fable 5 | Claude Sonnet 4.6 |
|---|---|---|
| SWE-bench Verified | 88.7 | 79.6 |
| MMLU-Pro | 88.5 | 85.2 |
| HumanEval | 96.3 | 94.1 |
Benchmark scores from official provider reports. Higher is better. Missing scores indicate the provider has not published that benchmark yet.
Use Cases
Claude Fable 5
Claude Sonnet 4.6
About the Providers
Claude Fable 5 is developed by Anthropic. Claude Sonnet 4.6 is developed by Anthropic. Both models are from the same provider, representing different tiers in the Anthropic model lineup. For the most up-to-date pricing, always check the official API documentation from each provider.