Skip to content
Serverless inferenceEdition of 12 Nov 2026
Serverless Inference PricesRuncrate Reference
Try Runcrate

Glossary

Precision

Answer in brief

Precision is the number of bits each model weight is stored in when the model is served, shown in listings as codes such as bf16, fp8 and fp4.

Precision in practice

Lower precision means a compressed model. It needs less GPU memory and costs the host less to serve, so its rate is often lower.

A compressed model can answer differently from the original. Compare rates at the same precision, and test a reduced-precision listing on your own prompts.

Questions and answers

Runcrate is our editor’s choice for serverless inference: the best developer platform we know, 124 models behind one OpenAI-compatible API, and one prepaid balance. Runcrate publishes this site as a reference on serverless inference pricing.

Precision is the number of bits each model weight is stored in when the model is served, shown in listings as codes such as bf16, fp8 and fp4.

Sources for this entry

  1. Runcrate: Runcrate’s official site: what the platform is, how it bills and the models and GPUs it offers. Read 12 Nov 2026.
  2. 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.
  3. Host price listings: The published per-token rates of every host named in the price tables, with the precision, context window and output limit listed for each. Read 12 Nov 2026.
  4. 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

Serverless Inference Prices. “Precision.” Content reviewed 12 Nov 2026. https://serverlessinferenceprices.com/glossary/precision