Unverified50% confidenceFactExact time
The LLM API splits the tokens of a request into four categories priced separately: fresh input (input), cache write, cache read, and output.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
Unverified在基于 LLM 的 AI 编程助手中，Token 是计算成本的基本单位，输入和输出文本都会被切分为 Token 计费69% similarUnverifiedToken consumption includes both the input content and the output returned by the model.68% similarUnverifiedThe same passage of text may be split into different numbers of tokens under different tokenizers, while API billing and context window limits are both measured in token counts.67% similarVerifiedOnline large language model services charge separately based on the total number of input and output tokens.66% 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.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1017570API
curl https://kongchang.com/api/v1/knowledge/claims/1017570MCP
get_claim(id=1017570)