Unverified60% confidenceFactExact time
Reasoning Tokens count toward max_output_tokens and billing, and output Tokens likewise consume TPM.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedReasoning tokens count toward TPM and billing, even if they do not appear in the final reply.77% similarUnverified在基于 LLM 的 AI 编程助手中，Token 是计算成本的基本单位，输入和输出文本都会被切分为 Token 计费65% similarVerifiedThe computational cost of generating output is typically far higher than that of processing input, and some vendors set separate quotas for input tokens and output tokens.65% similarUnverifiedThe LLM API splits the tokens of a request into four categories priced separately: fresh input (input), cache write, cache read, and output.62% 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.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1034046API
curl https://kongchang.com/api/v1/knowledge/claims/1034046MCP
get_claim(id=1034046)