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

Description and use

Token cost comparison between claude-in-chrome and opencli revealed that screenshot calls are ~5× more expensive than text calls. Opencli saves ~27 % tokens overall, especially on logged‑in web apps. Updated rule: use API, read page as text with opencli, and screenshot only for visual checks.

Problem

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

Outcome

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.

Workflow

• 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.

Evidence

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.

Source

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.

Source

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

Source

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.

Source