Unverified50% confidenceBenchmarkExact time
Based on measurements from more than 7,500 real API counts, the median call for claude-in-chrome returning a screenshot is 1,855 tokens, while the median call returning only text is 373 tokens, with screenshot calls at about 5 times text calls.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedIn a pydantic-ai test, after 10 parallel tool calls (21 new blocks), the next request read 6,827 tokens from cache; after 11 calls (23 blocks), the read count was 0 and 7,534 tokens were written again.70% similarUnverifiedThe median tokens per call for opencli is 397, roughly on par with claude-in-chrome's text-only calls (373), with the entire gap between the two coming from screenshots.67% similarUnverified父子分块策略用小块（128~256 Token）做精准检索，命中后返回其所属大块（512~1024 Token）作为上下文65% similarUnverifiedThe author reproduced it on a T4 with the same model and testing method: at 8 concurrency, a single request decodes at 122–124 tokens/s, and the whole server produces 701–708 tokens/s, likewise about a 5.7-fold difference.64% similarUnverifiedFor Gemini 4 Argon, the maximum output for synchronous requests is 65,536 tokens, and the maximum output for long decode is 1,048,576 minus the input tokens.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1033220API
curl https://kongchang.com/api/v1/knowledge/claims/1033220MCP
get_claim(id=1033220)