← Back to all comparisons
Side-by-side
Claude Sonnet 4.6 vs GPT-5
Anthropic vs OpenAI — head-to-head specs and pricing.
Anthropic
Claude Sonnet 4.6
Balanced speed + capability.
Sonnet is Anthropic's balanced model for general agents and chat.
OpenAI
GPT-5
OpenAI's flagship general-purpose model.
GPT-5 is OpenAI's flagship LLM — strong reasoning, tool use, vision, and JSON mode. Drop-in for anything you'd use GPT-4o for.
| Spec | Claude Sonnet 4.6 | GPT-5 |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Input cost / 1M tokens | $3.60 | $3.00 |
| Output cost / 1M tokens | $18.00 | $12.00 |
| Context window | 200,000 tokens | 256,000 tokens |
| Max output tokens | 16,000 | 16,000 |
| Streaming support | ✓ | ✓ |
| Tool calling | ✓ | ✓ |
| Vision input | ✓ | ✓ |
| JSON mode | — | ✓ |
| Status | ACTIVE | ACTIVE |
Use both via OneAPIKey — one key, one bill
OneAPIKey aggregates Anthropic, OpenAI, and 10 more providers behind a single API. Smart Routing automatically picks the best model per request — or you choose explicitly.
More comparisons: