Skip to navigation
Modelsspan-02

span-02

A decision model with anytime reasoning. span-02 answers typed questions about a state and returns a probability distribution for every answer.

span-02 is Respan’s decision model. Send a state (text or any JSON value, plus up to 4 images) and a set of typed questions. For each question, span-02 returns the answer with its full probability distribution, not generated text you have to parse.

Call it at POST https://api.respan.ai/api/v1/decisions with your Respan API key. The body is the System One format, so a System One client works by changing the URL. The API reference lists every field.

Question types

One request can mix all four types.

TypecriteriaAnswer fields
choiceAn object of option keys and descriptionschoice, probabilities, confidence
noulOptional true and false descriptionsnoul, the probability of yes
scoreA list of levels, from low to highscore (the probability-weighted level), legend, probabilities, confidence
numberNonenumber, text, confidence

number answers with the number itself, so you don’t list candidate values as options. Question types shows a request and response for each type.

Anytime reasoning

Reasoning models let you pick an effort level. span-02 takes a deadline instead: it thinks until the deadline, then answers with its best decision so far. Set it per request in reasoning:

FieldValuesDefault
modeauto thinks only when span-02 is unsure; on thinks for every question; off never thinksauto
budget_msThe thinking time for the request, in milliseconds, from 0 to 600000. 0 means no deadline.0
"reasoning": { "mode": "on", "budget_ms": 300 }

A per-question cap on thought length applies whatever budget_ms says. The thought itself is never returned, and its tokens aren’t billed.

Images

Send up to 4 images in images, as data URIs or base64. span-02 sees them before the text, so questions can ask about photos, documents or screenshots.

Billing and limits

  • Credits: span-02 runs on Respan credits only and is priced per input and output token. Without credits, a call returns 402.
  • Rate limit: span-02 has its own per-organization limit, separate from chat completions. Over it, a call returns 429.
  • No streaming: stream: true returns 400.
  • Model name: use span-02 or respan/span-02, or omit model. Any other name returns 400.
  • Timeouts: if span-02 doesn’t answer in time, the call returns 504. Retry, or send fewer questions or a shorter state.

Open weights

span-02’s weights and inference engine are on Hugging Face, with instructions for hosting it on your own GPU.