Unverified50% confidenceBenchmarkExact time
For Claude Code with 100 tools, enabling ToolSearch used 59% fewer input tokens per run than disabling search (19.9k vs 48.6k), but at list prices enabling search cost $0.047 per run while disabling search cost $0.038.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
UnverifiedThe extra ToolSearch calls make Claude Code more expensive than full loading below about 19 tools and cheaper above 19.73% similarUnverifiedThe price of prompt cache reads is only 0.05×–0.1× the normal input price (depending on the model), the Batch API enjoys a 50% discount when you can wait, and Anthropic charges an additional $10 per 1,000 searches for web search.67% similarUnverifiedAccording to the video author's calculation, enabling Tool Search makes the input Token cost about 5-9 times cheaper than the unoptimized version.61% similarUnverifiedOpenAI's official example shows that one write plus nine full reads totals 2.15× the prefix input price, compared to 10× without caching.58% similarUnverifiedIn search-intensive applications (such as research agents and shopping assistants), web search fees may exceed the token bill itself.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1031413API
curl https://kongchang.com/api/v1/knowledge/claims/1031413MCP
get_claim(id=1031413)