Unverified50% confidenceFactExact time
Large model services adopt a Token quota mechanism, where each model call consumes Tokens measured by the input and output text
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMainstream large model APIs charge separately for input tokens and output tokens, with input tokens typically including the entire conversation history (i.e., the context).77% similarUnverifiedtoken消耗的精确计量依赖于对Cursor官方API响应体中usage字段（包含prompt_tokens、completion_tokens）的实时解析75% similarUnverifiedAPI calls to large models are typically billed by the number of Tokens, and each model has a Token count limit for its context window72% similarUnverifiedThe context window refers to the complete set of input and output tokens visible to a large language model at any given moment, consisting of input tokens plus output tokens.70% similarUnverified该工具提供Token用量查看功能，用户需自行配置对话模型和生图模型69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/978842API
curl https://kongchang.com/api/v1/knowledge/claims/978842MCP
get_claim(id=978842)