Unverified50% confidenceFactExact time
A typical RAG query (2000-token prompt, 2500-token retrieved context, 400-token output) costs about $0.013 on a mid-tier model.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedTaking 100,000 queries per month, about 400 input tokens and 100 output tokens as an example, the monthly costs are: nova-micro $2.80, gpt-4o-mini $12.00, haiku-4.5 $90.00, sonnet-5.5 $180.0077% similarUnverifiedIn the warm cache case, a /compact request on a 136.4k token context costs about $0.056–$0.059, which is 1.8–1.9 times that of a normal turn (about $0.031).76% similarUnverifiedThe model input cost for 100,000 requests × 2,000 billed input tokens is about $8.40 (excluding retries, retrieval, moderation, and platform fees).74% similarUnverifiedUnder the same H100 configuration, the cost per million output tokens is about $0.22–0.23 under an 8-request concurrent load.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1037652API
curl https://kongchang.com/api/v1/knowledge/claims/1037652MCP
get_claim(id=1037652)