6 tools
LLM Parameter and Reference Tools
Parameters, encodings and behaviour, explained interactively.
Temperature, top-p, max_tokens and stop sequences are set once at the start of a project and rarely revisited, usually to whatever a tutorial suggested.
Each of them has a measurable effect on output quality, latency and cost. These tools show that effect rather than describing it.
- o200k_base vs cl100k_base ComparatorThe same text, both OpenAI encodings, exact counts.
- Temperature and Top-p SimulatorSee what temperature, top-p and top-k do to the same distribution.
- max_tokens PlannerSet the ceiling from your data, not from the model maximum.
- Streaming Latency SimulatorWhat streaming does to perceived speed, in numbers.
- LLM Pipeline Latency EstimatorAdd up a multi-step pipeline and find the step to fix.
- Context Rot VisualizerA fuller window is not a better one.
Which one you need
The sampling simulator is for understanding what temperature, top-p and top-k actually do to the distribution, which is hard to reason about from the documentation and easy to see once it is drawn.
The max_tokens planner is the practical one. Output is the expensive side and the ceiling has two failure modes: too low silently truncates good answers, unset leaves your bill bounded only by how much the model feels like writing.
Reasoning token estimation matters on any model that thinks before answering, because those tokens are billed at the output rate and never appear in the output. Budgeting from visible answer length can understate the cost several times over.
The general rule underneath this category: the defaults were chosen by someone else for a general audience. Anything that must be reproducible belongs at temperature zero, and that includes every grader.
Questions
What temperature should I use?
Zero for anything that must be reproducible — classification, extraction, routing, and any model acting as a grader. Higher only where variety is the point. The value is also not calibrated across model families, so a setting carried from another provider is a guess.
Should I set both temperature and top-p?
Usually not. They interact in ways that are hard to reason about, and teams that tune both typically end up with a combination they cannot explain or reproduce. Change one and leave the other at its neutral value.