Unverified50% confidenceFactExact time
Billing for model input and output and occupancy of the context window are both measured in token counts.
1
Sources
50%
Confidence
Long-term
Relevance
11/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThinking is enabled by default, and the reasoning tokens it generates are billed as output tokens and counted toward max_tokens.75% similarUnverifiedUnder the mechanism in which large models bill by input and output tokens, resending the full browsing history every day causes the input token cost to grow linearly with the number of days of use; having the client perform deduplication, aggregation, or incremental summarization can keep the input volume at a roughly constant level.75% similarUnverifiedThe context window refers to the maximum number of tokens a single request can hold (input plus output); the larger the window, the higher the cost per call.74% similarUnverifiedA large model's context window refers to the upper limit of tokens a single call can receive; anything beyond that is truncated or causes an error, and APIs usually bill by input tokens, so the longer the history, the higher the cost per call.74% similarUnverifiedToken efficiency refers to the ratio between the total number of tokens a model consumes to complete a specific task and the output quality; under the token-based billing model, it directly determines usage cost.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1125979API
curl https://kongchang.com/api/v1/knowledge/claims/1125979MCP
get_claim(id=1125979)