Community tool compares anonymous request-token counts between Claude Opus 4.6 and Opus 4.7 on real prompts

A new open source page collects anonymous community-submitted prompts to compare request-token usage between Opus 4.6 and Opus 4.7. It reports community averages from real inputs, stores only anonymous submission IDs, and notes it is not affiliated with Anthropic.

Token-count comparisons can help developers estimate cost and context behavior when evaluating model upgrades. Community-sourced benchmarking reflects a broader trend toward practical AI observability tools built outside official vendor dashboards.