Unverified50% confidenceFactExact time
Thinking is enabled by default, and the reasoning tokens it generates are billed as output tokens and counted toward max_tokens.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
UnverifiedPer-request billing is flat and predictable; per-token billing is a function of input, output, and the number of loop retries, so the cost shape is different.77% 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.73% 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.72% similarUnverifiedCost per task = input tokens × input unit price + output tokens (including thinking tokens) × output unit price.71% similarUnverifiedMoving retrieval up front into the system prompt increases the number of input tokens per call, thereby increasing cost, but it improves the determinism of memory use.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1067672API
curl https://kongchang.com/api/v1/knowledge/claims/1067672MCP
get_claim(id=1067672)