Token Bleed
Silent budget drain from re-onboarding — tokens spent re-explaining context the system should already hold.
Token Bleed is one of the most expensive problems in AI today, and most teams don't even know they have it. Every time a user starts a new session and re-explains their project, their preferences, their codebase structure, and their constraints, they're spending tokens on information the system should already know. It's like hiring a contractor who gets amnesia every night — you pay them to re-learn your project every morning before they can do any work. The cost is silent because it's baked into every session rather than appearing as a single line item.
More in Reasoning Cost
Reasoning Tax
Extra model cost paid to compensate for context debt.
Token Burn
Token waste caused by a client sending the entire session history to the LLM on every call.
Context Compensation
The model using additional reasoning to make sense of poor, bloated, or unstructured context.
Reasoning Inflation
More reasoning is required to extract the same signal from worse context.
Reasoning Load
The amount of interpretive work a model must perform before useful task execution begins.
Cognitive Drag
Friction introduced by poorly structured context.
Reasoning Efficiency
The model producing correct output with minimal interpretive overhead — the reward for clean context.
Token Leverage
Getting more useful output per token spent. The inverse of Token Bleed.