Verified80% confidenceFactExact time
The per-token inference cost of Flash models is typically one order of magnitude lower than that of Pro-level models.
4
Sources
80%
Confidence
Long-term
Relevance
5/22/2026
First Seen
Sources
Gemini 3.5 Flash Achieves a Massive Leap on the GDPval Benchmark
twitterOfficialLoganK5/22/2026
Related Entities
Related Claims
UnverifiedThe concurrent requests per second for flash-series lightweight models may far exceed those of flagship models, and when a rate mismatch applies flagship model pricing, the difference may be 5 to 10 times.79% similarUnverified轻量版模型单次推理的算力消耗往往只有旗舰版本的十分之一甚至更低70% similarUnverifiedJF revealed that in 95% or even more cases, scores given by smaller models such as Flash or Flash-Lite as judges are consistent with those of larger models, meaning the judging step often does not require expensive Pro large models.69% similarUnverifiedFlash模型的首Token延迟（TTFT）通常比Pro低50%以上68% similarUnverifiedQwen3.8 Flash Next has a sparsity rate of approximately 95%, using less than 5% of its parameters per inference.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/40046API
curl https://kongchang.com/api/v1/knowledge/claims/40046MCP
get_claim(id=40046)