Unverified50% confidenceFactExact time
The Anthropic Messages API splits token tracking into input tokens per minute (ITPM) and output tokens per minute (OTPM), plus the standard RPM.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
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).67% similarUnverifiedtoken消耗的精确计量依赖于对Cursor官方API响应体中usage字段（包含prompt_tokens、completion_tokens）的实时解析65% similarUnverifiedA prompt cache hit requires the request prefix to be byte-for-byte identical to what was written at cache time; mixing dynamic content such as timestamps or session IDs into system prompts will cause frequent cache invalidation.64% similarUnverifiedCoding agent frameworks add an additional 8,000 to 30,000 tokens of system prompts to each message sent to the model.64% similarVerifiedAPI billing covers both input tokens and output tokens, and as a conversation extends, the input tokens carried in each request grow linearly.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1033773API
curl https://kongchang.com/api/v1/knowledge/claims/1033773MCP
get_claim(id=1033773)