Skip to main content
Nimble is a family of models from Bespoke Labs. Every Nimble model answers with probabilities, so you can set your own thresholds. You call every model at the same endpoint, POST https://api.bespokelabs.ai/v1/systemone. The model field in the request picks the model. nimble-latest is the newest general Nimble model, which is nimble-v3 now. Use nimble-latest to get each new model when it comes out. Use nimble-v3 to stay on this model. bespokelabs/Bespoke-Nimble-9B-v3 is another name for nimble-v3. The previous model is still available as bespokelabs/Bespoke-Nimble-9B. Fact check and code search each come in three sizes:
  • The -lite model is the fastest and the cheapest. A small model answers every question.
  • The model with no suffix, e.g., nimble-factcheck, is in between. The small model answers every question first. Then a larger model answers again the questions that the small model is unsure about.
  • The -max model is the most accurate and costs the most. It uses the largest models.

The request format

Every model takes the same request format, which is called System One. A request has three fields:
  • model names the model.
  • state is the text or JSON to ask about.
  • questions maps your own question IDs to questions. The answers use the same IDs.
You can send the requests with plain HTTP. You can also use the bespokelabs Python SDK or TypeSafe’s Python SDK. The path /v1/nimble/systemone takes the same requests as /v1/systemone. The bespokelabs SDK uses that path. The general models have three types of question:
  • A noul question asks whether a statement is true. The answer is the probability that it is true.
  • A choice question asks which of 2 to 255 options fits best. The answer names the most likely option and gives the probability of every option.
  • A score question asks where the state falls on a scale of 2 to 255 ordered levels. The answer is the expected level.
Fact check takes only noul questions. Code search takes noul questions, and it also accepts boolean questions, which it answers the same way.

Quickstart

Get a key and make your first request.

Question types

Write noul, choice, and score questions and read the answers.

Pricing

What each model costs and how Nimble counts tokens.

API reference

The full request and response format.