Nimble

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. Fact check comes 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 or with TypeSafe’s Python SDK. The path /v1/nimble/systemone takes the same requests as /v1/systemone. 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.