Your browser agent pays to look at pictures: opencli vs claude-in-chrome token use

说明与用途

claude-in-chrome 与 opencli 的令牌成本比较显示，截图调用比文本调用昂贵约5倍。opencli 在整体上节省约27%的令牌，尤其是在登录的 Web 应用上。更新规则：使用 API，使用 opencli 读取页面文本，仅在需要视觉检查时截图。

问题

Determine token cost differences between Claude Code’s claude-in-chrome and opencli when interacting with web pages.

结果

Screenshot calls cost ~5× more tokens than text calls; 23% of claude-in-chrome calls were screenshots, accounting for 49% of tokens. Opencli’s median tokens per call (397) matched claude-in-chrome text calls (373). Across nine sites, opencli saved ~27% tokens per call overall, especially on logged‑in web apps.

工作流

• Collect 7,500+ browser tool calls from Claude Code logs.
• For each call, record API token counts before and after the call.
• Calculate token difference per call.
• Aggregate median tokens per call type for claude-in-chrome (screenshot vs text).
• Compare median tokens per call for opencli.
• Analyze token savings per site across nine websites with ≥10 calls each.
• Derive overall token savings and update clickops rule.

证据

We went through our own Claude Code session logs: 7,500+ browser tool calls. For each call, we took the token counts the API reported before and after it. The difference is how many tokens that call's result added to the context.

来源

A screenshot call cost about 5x a text call. The 23% of calls that returned screenshots made up 49% of all claude-in-chrome tokens.

来源

opencli won on 7 of the 9 sites, about 27% fewer tokens per call when weighted by call count.

来源

Our clickops rule now: 1) Use the API or curl when one exists. 2) Read the page as text with opencli. 3) Take a screenshot only to check something visual.

来源