Skip to main content
POST
Choose a label
  • Returns one JSON response; streaming, video, tools, and generation controls are not supported.
  • Local requests’ text and schema, excluding images, must fit within 64 KiB, and the whole request within 32 MiB, including base64 and JSON. The complete input must fit the loaded context window. Nimble and Tev also require two token positions for scoring. Input is never truncated.
  • Cloud models need a paid plan or purchased usage credits. Cloud requests accept up to 64 questions, named with up to 100 ASCII letters, digits, _, ., or -, and up to 4 images of at most 4 MiB and 16 megapixels each, 8 MiB in total. Requests must fit within 13 MiB, and input must fit the model’s 65,536-token context window.

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
model
string
required

Model trained for System One, such as nimble, or clef:cloud for Ollama's cloud.

Pattern: \S
state
required

A nonempty string, or an object or array serialized as JSON text. Not interpreted as chat messages or multimodal input.

Pattern: \S
questions
object
required

Named questions about the shared state. Answers are not passed to later questions. Cloud models accept names of up to 100 ASCII letters, digits, _, ., or -.

images
string<byte>[]

Base64-encoded images shared by all questions, in request order. Requires a model with vision, such as Clef. Models with audio input also accept WAV clips here. URLs and data URLs are not supported.

keep_alive

How long to keep the model loaded after the request, as a duration string (such as 5m) or seconds. Zero unloads after the request; a negative value keeps it loaded. Defaults to the server's keep-alive setting (5m unless configured otherwise).

Response

Answers and token usage for all questions. Example probabilities and confidence are rounded to four decimal places; results and usage can vary with the model and server configuration.

model
string
required

Model name from the request.

answers
object
required

Answers keyed by the question names in the request.

usage
object
required