Model comparison
Claude Sonnet 4.6 vs o1
Anthropic
Claude Sonnet 4.6
The pragmatic default — Claude quality without Opus pricing.
OpenAI
o1
The first reasoning model — historically important, now superseded.
Specs
| Metric | Claude Sonnet 4.6 | o1 |
|---|---|---|
| Context window | 1M tokens↑ | 200K tokens |
| Input $/1M tokens | $3.00↑ | $15.00 |
| Output $/1M tokens | $15.00↑ | $60.00 |
| Modalities | Text · Image | Text · Image · File |
| Open weights | No | No |
| Released | — | Dec 2024 |
Capability differences
| Capability | Claude Sonnet 4.6 | o1 |
|---|---|---|
| Tool use | Yes | No |
| Vision | Yes | No |
| Prompt caching | Yes | No |
Key differences
- —Claude Sonnet 4.6 offers 1M context; o1 offers 200K.
- —Input pricing: Claude Sonnet 4.6 at $3.00/1M vs o1 at $15.00/1M.