LLM cost comparisons

Each comparison puts two models side by side using only the provider's published prices and limits (see the LLM API pricing page for sources and dates), then works out what typical workloads cost on each. They compare cost, not quality: test both models on your own task before switching.

• Claude Opus 5.5 vs Claude Sonnet 5.5
• Claude Haiku 5.5 vs Claude Sonnet 5.5
• Claude Sonnet 4.6 vs Claude Sonnet 5.5
• Claude Opus 4.7 vs Claude Opus 5.5

Compare any other models with your own token counts in the LLM cost comparator, or see what common workloads cost across every listed model.