Model comparison
Claude Sonnet 4.6 vs Claude Sonnet 5
A spec-by-spec comparison of Claude Sonnet 4.6 and Claude Sonnet 5: pricing, context window, capabilities, and independently sourced benchmarks.
Head-to-head
- Claude Sonnet 5 costs 1.5x less per input token than Claude Sonnet 4.6 ($2.00/MTok vs $3.00/MTok).
- Claude Sonnet 4.6 and Claude Sonnet 5 share the same 1,000,000 tokens context window.
| Spec | Claude Sonnet 4.6 | Claude Sonnet 5 |
|---|---|---|
| Provider | anthropic | anthropic |
| Family | Claude Sonnet | Claude Sonnet |
| Status | legacy | frontier |
| Release date | 2026-02-17 | 2026-06-30 |
| Knowledge cutoff | 2025-08 | 2026-01 |
| Context window | 1,000,000 tokens | 1,000,000 tokens |
| Max output tokens | 128,000 tokens | 128,000 tokens |
| Input price | $3.00/MTok | $2.00/MTok |
| Output price | $15.00/MTok | $10.00/MTok |
| Cached input price | $0.30/MTok | $0.20/MTok |
| Vision | Yes | Yes |
| Tool use | Yes | Yes |
| Extended thinking | Yes | Yes |
| Streaming | — | — |
Claude Sonnet 4.6
Strengths- Uses the older Claude tokenizer, so the same text bills ~30% fewer tokens than on Sonnet 5.
- Carries the full 1M-token context window at standard pricing.
- Superseded by Claude Sonnet 5, which is cheaper until 2026-08-31 and the same price after.
- Tool-use system prompt overhead is 497 tokens on auto against 354 on Sonnet 5.
Claude Sonnet 5
Strengths- Carries the full 1M-token context window at standard pricing.
- Cheapest 1M-context model from any US lab in this file.
- The scheduled 2026-09-01 increase to $3/$15 was cancelled; $2/$10 is Anthropic’s stated standard price, not a temporary one.
- Uses the newer Claude tokenizer, ~30% more tokens for the same text than Sonnet 4.6 and earlier.
- Anthropic lists classic extended thinking as not supported; only adaptive thinking is available.
Not sure which one to use?
Flaibo is a daily AI orientation hub: a 12-week path and a prompt vault, with Free and Professional plans. Build the habit, not just the comparison.
Start your AI path