Unverified50% confidenceFactExact time
In the scenario of a 1,280-token request plus a 108-token answer, total input cost still exceeds output even if the output price is five times higher.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPerplexity has reduced the input token price of the Decision API to 2 cents per million tokens.78% similarVerified大模型API中输出Token的单价通常是输入Token的2-4倍75% similarVerifiedThe unit price of output tokens is approximately 5 times that of input tokens.75% 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).75% similarUnverifiedMainstream API pricing is based on per million tokens (MTok), and the unit price of output tokens is typically 2–4 times that of input tokens, because output requires autoregressive generation token by token.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1067113API
curl https://kongchang.com/api/v1/knowledge/claims/1067113MCP
get_claim(id=1067113)