Unverified50% confidenceFactExact time
Throughput refers to the number of tokens or requests the system processes per unit of time.
1
Sources
50%
Confidence
Long-term
Relevance
10/29/2026
First Seen
Sources
Related Entities
Related Claims
Unverified大模型调用的计费单位是Token而非请求次数，响应时间从毫秒级变为秒级甚至分钟级75% similarUnverifiedContext length refers to the upper limit on the number of tokens a model can process at once, and when running locally, the longer the context, the more memory is used.73% similarUnverifiedThe billing dimension of LLM gateways has changed from "number of requests" to "number of input and output tokens," requiring precise metering and quota management.73% similarUnverified激活参数描述的是每个 token 的计算量，而非权重的存储需求71% similarUnverifiedThe autoregressive generation phase is a memory-bandwidth-sensitive workload: generating each token requires reading the model weights in full once (or at least reading the weights involved in the activation path), so the actual speed is approximately equal to the VRAM bandwidth divided by the weight volume that needs to be read per token.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1110180API
curl https://kongchang.com/api/v1/knowledge/claims/1110180MCP
get_claim(id=1110180)