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The first reasoning model — historically important, now superseded.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