Unverified50% confidenceFactExact time
Token consumption includes both the input content and the output returned by the model.
1
Sources
50%
Confidence
Long-term
Relevance
10/10/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedOnline large language model services charge separately based on the total number of input and output tokens.73% similarVerifiedTokens are the basis for billing by large models; they are produced by a tokenizer splitting raw text and are the basic unit by which large models process text.73% similarUnverifiedThe cost of each large language model call consists of two parts: input tokens (Prompt) and output tokens (Completion).72% similarUnverified语义缓存通过将用户请求转化为向量嵌入，在向量空间中计算语义相似度，将语义相近的问题映射到同一缓存结果，从而减少模型调用次数和Token消耗71% similarUnverifiedLarge language model APIs are generally billed by the total number of input plus output tokens, and re-injecting historical context on every call in long projects causes token consumption to balloon rapidly.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/993704API
curl https://kongchang.com/api/v1/knowledge/claims/993704MCP
get_claim(id=993704)