Expired90% confidenceFactTime unknown
GPT-4o has different prices for input tokens and output tokens, and a single complex Agent call may involve multiple rounds of model interaction, causing the actual number of tokens consumed to far exceed users' intuitive expectations.
1
Sources
90%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedThe token price of GPT-4-level models can be 10 to 100 times that of smaller models; token routing/model cascading strategies use small models for simple tasks and only invoke large models for complex reasoning to control costs.79% similarUnverifiedMainstream large model APIs such as OpenAI GPT-4o and Anthropic Claude both use a per-token billing model, with input and output tokens priced separately.77% similarVerifiedThe input Token price for GPT-4 is approximately 1/3 of the output Token price.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/25740API
curl https://kongchang.com/api/v1/knowledge/claims/25740MCP
get_claim(id=25740)