Unverified70% confidenceFactExact time
Each model invocation calculates both input tokens and output tokens simultaneously, and both together determine the cost of a single call.
2
Sources
70%
Confidence
Long-term
Relevance
8/29/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedEach model invocation consumes both input tokens (prompts and context) and output tokens (the model's generated response), with the two typically priced separately.79% similarUnverifiedLarge models are billed by the number of input plus output Tokens for each inference.79% similarUnverifiedToken Plans with shared quotas across multiple models involve model conversion rate issues, where the billed tokens consumed per call for different models may not equal the actual number of text tokens processed.76% similarUnverifiedA model's compute cost is approximately quadratic with sequence length (due to the attention mechanism), so billing by token reflects real compute consumption76% similarUnverifiedThe reasoning tokens produced by reasoning models share the same max_tokens budget as the final output, and they are billed as usual even if the visible reply is an empty string.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/820899API
curl https://kongchang.com/api/v1/knowledge/claims/820899MCP
get_claim(id=820899)