Unverified50% confidenceFactExact time
According to an analysis based on real API traffic, out of about 411,000 requests over 7 days, 99.3% of processed tokens were input tokens; the median request had 3,782 input tokens and returned only 147 tokens.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe payload size returned by different search APIs can differ by orders of magnitude—for the same query, one API may return 800 tokens while another may return 8,000 tokens.73% similarUnverifiedEach retry resends the complete prompt input tokens and is billed in full; a request with 4,000 input tokens retried 3 times will consume 16,000 tokens.71% similarUnverifiedIn agentic scenarios where system prompts run to thousands of tokens, if more than 90% of requests hit the cache, the effective input cost per request may be only 5%–10% of the listed price.69% similarUnverifiedThe prefill throughput of this setup increases with prompt length, climbing from approximately 290 tokens/s for short prompts to approximately 1,300 tokens/s, with an average prefill throughput of approximately 900 tokens/s.66% similarUnverified在Pi里说一句你好只占用约1100的上传Token，仅消耗上下文窗口的千分之四；而在Codex里打招呼要消耗18000 Token，约占7%的上下文窗口66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1037059API
curl https://kongchang.com/api/v1/knowledge/claims/1037059MCP
get_claim(id=1037059)