Unverified50% confidenceFactExact time
Xisu AI bills by actual token usage, charging after the request completes, with usage recorded in the request log; amounts are calculated to ten decimal places.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
Related Entities
Related Claims
UnverifiedSizing backfill by fact count is a poor approximation, since model cost is a function of text; batches began to be limited by text volume, capped at about 8000 characters; a full backfill of about 524 facts was estimated at 3.4 minutes, completed in about 19 batches.62% similarUnverifiedCache Hit Rate refers to the proportion of requests in which an AI model is able to reuse already-cached context (prompt prefixes) when processing requests; the higher the hit rate, the lower the API cost for the same workload.61% similarUnverifiedFor medium tasks such as batch file processing, a consumption range of single digits to a dozen or so credits is normal.61% similarUnverifiedIn the field of generative AI, rate limiting solely by requests per minute (RPM) is an ineffective metric, because one request carrying a large context payload can consume 100,000 tokens while another request consumes only 250 tokens.60% similarUnverifiedSetting a minimum number of samples per query (for example 5 to 10) and recording the mention rate and its range of fluctuation is a reasonable AI visibility measurement practice.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1062266API
curl https://kongchang.com/api/v1/knowledge/claims/1062266MCP
get_claim(id=1062266)