Model comparison
Claude Sonnet 4.6 vs o3
Anthropic
Claude Sonnet 4.6
The pragmatic default - Claude quality without Opus pricing.
OpenAI
o3
OpenAI's mainstream reasoning model - production-viable thinking.
Specs
| Metric | Claude Sonnet 4.6 | o3 |
|---|---|---|
| Context window | 1M tokens↑ | 200K tokens |
| Input $/1M tokens | $3.00 | $2.00↑ |
| Output $/1M tokens | $15.00 | $8.00↑ |
| Modalities | Text · Image · File | Image · Text · File |
| Open weights | No | No |
Capability differences
| Capability | Claude Sonnet 4.6 | o3 |
|---|---|---|
| Vision | Yes | No |
| Prompt caching | Yes | No |
Key differences
- -Claude Sonnet 4.6 offers 1M context; o3 offers 200K.
- -Input pricing: Claude Sonnet 4.6 at $3.00/1M vs o3 at $2.00/1M.