Unverified70% confidenceFactTime unknown
主流商业模型如GPT-4o的输出速度通常在50-100 TPS区间
1
Sources
70%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedGPT-4-level models typically achieve 30–80 TPS on consumer-grade APIs, while optimized small models or dedicated inference hardware can reach 200+ TPS.83% similarUnverifiedModern models such as GPT-4o support context lengths of tens of thousands to over one hundred thousand tokens76% similarVerifiedThe cost of calling GPT-4o is approximately 15–20 times that of GPT-4o-mini.74% similarVerifiedThe single-call latency of GPT-4-level models may fluctuate between 1 and 30 seconds.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/10197API
curl https://kongchang.com/api/v1/knowledge/claims/10197MCP
get_claim(id=10197)