Unverified50% confidenceFactExact time
输出Token定价高于输入Token是因为Prefill阶段可并行矩阵运算而Decode阶段必须串行自回归解码，Decode阶段GPU吞吐量约为Prefill阶段的1/6到1/10
1
Sources
50%
Confidence
Long-term
Relevance
7/23/2026
First Seen
Sources
Related Claims
UnverifiedThe Prefill phase is a compute-intensive operation, while the Decode phase is a memory-bandwidth-intensive operation.75% similarUnverifiedGPU utilization during the decoding phase of large language model inference is far lower than during the prefill phase's parallel matrix computation, because decoding is a step-by-step autoregressive generation process75% similarUnverifiedConstrained Decoding computes the set of valid tokens at each token step of autoregressive generation based on a finite state machine or context-free grammar and renormalizes the probabilities, mathematically guaranteeing that the output conforms to the target schema.69% similarUnverified自回归生成每个Token都需要完整的前向传播，而输入只需一次编码，这是输出比输入贵的成本结构原因68% similarVerifiedLarge language model inference is divided into two phases, prefill and decode: prefill is compute-intensive and sensitive to GPU processing power, while decode is a memory-bandwidth-bound task.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/594429API
curl https://kongchang.com/api/v1/knowledge/claims/594429MCP
get_claim(id=594429)