Unverified50% confidenceFactExact time
The usage field in the Messages API has always been used to return the token statistics of the current call (such as input_tokens, output_tokens).
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedToken consumption includes both the input content and the output returned by the model.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.67% similarUnverifiedThe LLM API splits the tokens of a request into four categories priced separately: fresh input (input), cache write, cache read, and output.66% similarVerifiedOnline large language model services charge separately based on the total number of input and output tokens.65% 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.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1040069API
curl https://kongchang.com/api/v1/knowledge/claims/1040069MCP
get_claim(id=1040069)