Unverified50% confidenceFactExact time
The per-request models feature was introduced by commit a4ba394.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedNext-generation search services such as the Perplexity API, Exa, and Tavily offer built-in synthesis functionality that uses large models to summarize and reorganize retrieved results.53% similarUnverifiedThe GLM-4 series introduced tool-calling capabilities including function calling, code interpreter, and web search52% similarUnverifiedModel Routing implementation strategies include rule-based matching on keywords and task types, tiered strategies based on request token length, and using small classification models to identify request intent before dispatching51% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/900777API
curl https://kongchang.com/api/v1/knowledge/claims/900777MCP
get_claim(id=900777)