Verified65% confidenceFactExact time
API billing covers both input tokens and output tokens, and as a conversation extends, the input tokens carried in each request grow linearly.
3
Sources
65%
Confidence
Long-term
Relevance
7/16/2026
First Seen
Sources
Related Claims
VerifiedMainstream large model APIs charge separately for input tokens and output tokens, with input tokens typically including the entire conversation history (i.e., the context).80% similarVerifiedAPI billing typically distinguishes between input tokens and output tokens; in multi-turn conversations, the outputs from earlier turns become inputs in later turns and are billed again.77% similarUnverifiedUnder the continuation protocol, each continuation resends the prompt plus the already-decoded content, so the cumulative input token count grows far faster than the context.74% similarUnverifiedMainstream large-model APIs bill by input tokens and do not retain server-side session state, causing the same log segment to be counted as input tokens again in subsequent turns.74% similarUnverifiedInput token billing for the Decision API typically covers the user's incoming prompt and retrieved recall content, while output tokens correspond to the final result returned by the model.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/526416API
curl https://kongchang.com/api/v1/knowledge/claims/526416MCP
get_claim(id=526416)