opendunes

Span-01 Lite

by RespanReleased 26 September 2026

Scores a conversation against behaviours you describe in plain words and returns a probability for each, for high-volume evaluation and monitoring where volume matters more than peak accuracy; the lighter tier of Span-01

TakesText
GivesClassification

What it can do

What Respan states, checked against two benchmark sites.

Nothing more is published about this model yet.

Limits

The hard numbers — what it can take in, what it can give back, and where it stops.

Context window
not stated
Max output
not stated
Reads at once
not stated
Longest reply
not stated
Tokenizer
Other
Released
26 Sep 2026
Full API reference

Questions about Span-01 Lite

Is Span-01 Lite still on sale?

No. Respan has retired it. Other Respan models are on sale.

What is Span-01 Lite best for?

Scores a conversation against behaviours you describe in plain words and returns a probability for each, for high-volume evaluation and monitoring where volume matters more than peak accuracy; the lighter tier of Span-01.

Does Span-01 Lite work in Arabic, French or Darja?

Respan names no languages for Span-01 Lite. Arabic, French and Darja: not stated.

What can it answer?

Yes or no, one choice from your list, or a score on your scale. Each answer comes with its probability.

Who makes Span-01 Lite, and when was it released?

Respan. Released 26 September 2026.

Other Respan models, priced in dinars

See all Respan models
Span-02Respan · Oct 16, 2026

Respan Span-02 looks at a situation in text and images and settles the questions you set: choosing one option from several, giving a yes, no or unknown, or rating on a scale. It suits checking, guarding, routing and keeping watch over what AI systems produce across large volumes, and you can download it and run it yourself. It replaces Span-01, which reads text only and gives the chance that each behaviour you describe is present.

131 pages per call
≈0,0033 DAper case
View model
Span-01Respan · Sep 26, 2026

Respan Span-01 reads a conversation excerpt and, for each behaviour you describe in plain words, returns the chance that it is present. Use it to check, guard and keep watch over what AI systems say across large volumes. Within its family it is the tier that aims for accuracy, while the free Span-01 Lite is the lighter one.

≈0,0067 DAper case
View model