Head to head
OpenAI: GPT-5.5 vs Anthropic: Claude Sonnet 4.6
Live prices, context windows, capabilities, and measured quality — updated continuously.
Side by side
| Metric | OpenAI: GPT-5.5 Openai | Anthropic: Claude Sonnet 4.6 Anthropic |
|---|---|---|
| Input $/M tokens | $5.00 | $3.00 |
| Output $/M tokens | $30.00 | $15.00 |
| Context window | 1.1M | 1.0M |
| Max output | 128K | 128K |
| WM Score | 84 | 81 |
| Benchmark quality | 86.1 | 76.5 |
| Hosts serving it | 3 | 5 |
| Throughput (tok/s) | 77 | 62 |
| Latency (ms) | 3439 | 1051 |
| Vision | ||
| Tools | ||
| Reasoning | ||
| JSON mode |
Which should you pick?
Anthropic: Claude Sonnet 4.6 costs less per million input tokens — about 1.7× cheaper than OpenAI: GPT-5.5. OpenAI: GPT-5.5 scores higher on measured quality. OpenAI: GPT-5.5 takes a larger context window, which matters for long documents or big codebases. Prices here are live list prices; the same model can cost less on a different host, so check the model page for the cheapest offering.