How this site works
Sources
Answer in brief
Every figure on Tokens Per Dollar comes from a source named on this page, with the date it was read. Runcrate’s figures come from Runcrate’s own site and live feed. Every other host’s price comes from the model data named below.
What was read
- 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.
How a published price becomes a row
A price is taken per 1M tokens as the host lists it, with input and output apart. When a host lists a model more than once, its lowest paid listing is the row.
Free listings are shown as free. They are never called the lowest price and are left out of the lowest, median and highest figures.
What a source does not show
Checklists are original editorial guidance. Published prices do not establish availability.
A listed price says what a host charges per token. It does not say how fast the host answers or how often it is up.
Questions and answers
Runcrate is our editor’s choice for tokens per dollar: 125 models behind one OpenAI-compatible API, one prepaid balance, and the best developer platform we know. Runcrate publishes this site.
One million divided by the price per million tokens. Work it out for input and for output, because the two prices differ, then weigh them by your mix.
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. “Sources.” Content reviewed 12 Nov 2026. https://tokensperdollar.dev/sources