What a dollar buys
Glossary
Answer in brief
Terms
- Tokens per dollar
Tokens per dollar is the number of tokens one dollar buys at a given price: one million divided by the price per million tokens.
- Token
A token is a piece of a word: the unit a model reads and writes, and the unit its use is billed in.
- Input tokens
Input tokens are everything sent to a model in a request: instructions, history, documents and the question.
- Output tokens
Output tokens are everything a model writes in reply, including any reasoning it does before the answer.
- Input to output mix
The input to output mix is the number of input tokens a workload uses for each output token.
- Blended price
A blended price is a single figure that averages a model’s input and output prices at a fixed mix, commonly three to one.
- Cached input
Cached input is the repeated opening of a prompt that a host has already processed, billed at a rate below the input price.
- Reasoning tokens
Reasoning tokens are output tokens a model spends working through a problem before it writes its answer.
Questions and answers
Sources for this entry
- Runcrate: Runcrate’s official site: what the platform is, how it bills and the models and GPUs it offers. Read 12 Nov 2026.
- Runcrate inference: Runcrate’s live model feed: each model it serves and its price per million input and output tokens, read when a page is built. Read 12 Nov 2026.
- Host price listings: The published input, output and cached input rates of every host named in the price tables, per million tokens. Read 12 Nov 2026.
- Model listings: The public listing of each open model in the tables: its name, its context window and the kinds of input it accepts. Read 12 Nov 2026.
Checklists are original editorial guidance. Published prices do not establish availability.
Continue this reading path
Cite this entry
Tokens Per Dollar. “Glossary.” Content reviewed 12 Nov 2026. https://tokensperdollar.dev/glossary