Deployment

Token Budget

Definitie

The total number of tokens allocated for a model request, encompassing both input (prompt + context) and output. Managing token budgets is central to controlling inference cost in production LLM applications, especially when processing long documents or maintaining conversational history.

Gerelateerde Termen

Context Window

The maximum amount of text (measured in tokens) an LLM can process in a single request, encompassing both the prompt and the generated output. Larger context windows—now exceeding 1 million tokens in some models—enable processing of long documents, codebases, and meeting transcripts in one pass.

Inference Cost

The compute and financial cost of running a model to produce a single prediction or generated response. Inference cost is often the dominant AI operational expenditure at scale and is managed through model compression, caching, quantization, and batching strategies.

Prompt Cache

A technique that caches the key-value (KV) attention states of a repeated prompt prefix, so subsequent requests reuse the pre-computed computation rather than re-running it. Prompt caching reduces latency and cost significantly for applications with long system prompts.

Hulp Nodig bij het Begrijpen van AI?

Boek een consultatie om te bespreken hoe AI-concepten op uw uitdagingen van toepassing zijn.