Claude Sonnet 4.6 vs Claude Sonnet 5
Detailed comparison of API pricing, technical specifications, and benchmark scores. Updated 2026-06-29.
Cost at a Glance
Claude Sonnet 4.6 is 1.5× more expensive than Claude Sonnet 5 (33.3% savings if you switch).
At 5M input + 2M output tokens per month:
Choosing Claude Sonnet 5 could save you $15.00/mo
Price Comparison (per 1M tokens)
| Metric | Claude Sonnet 4.6 | Claude Sonnet 5 |
|---|---|---|
| Input (per 1M tokens) | $3.00 | $2.00 |
| Output (per 1M tokens) | $15.00 | $10.00 |
| Cache Write (per 1M tokens) | $3.75 | $2.50 |
| Cache Read (per 1M tokens) | $0.30 | $0.20 |
| Batch Input (per 1M tokens) | $1.50 | $1.00 |
| Batch Output (per 1M tokens) | $7.50 | $5.00 |
Prices are per 1 million tokens. Actual costs depend on your monthly token volume. Use the calculator →
Specifications
| Spec | Claude Sonnet 4.6 | Claude Sonnet 5 |
|---|---|---|
| Context Window | 1M | 1M |
| Max Output Tokens | 128K | 128K |
| Knowledge Cutoff | 2026-03 | 2026-01 |
| Modalities | Text, Image | Text, Image |
| Prompt Caching | Yes | Yes |
| Batch API | Yes | Yes |
| Thinking / Reasoning | Yes | Yes |
Benchmark Scores
| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5 |
|---|---|---|
| SWE-bench Verified | 79.6 | 82.1 |
| MMLU-Pro | 85.2 | 86.5 |
| HumanEval | 94.1 | 94.8 |
Benchmark scores from official provider reports. Higher is better. Missing scores indicate the provider has not published that benchmark yet.
Use Cases
Claude Sonnet 4.6
Claude Sonnet 5
About the Providers
Claude Sonnet 4.6 is developed by Anthropic. Claude Sonnet 5 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.