by RespanReleased 16 October 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.
You pay for what each request uses. No subscription, no minimum.
One case, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Text tokens | 3,33 DA |
per 1M tokens
One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send.
| Provider | ↑ Sent | Latency | Uptime |
|---|---|---|---|
| Respan | 3,33 DA | … | … |
You pay the price of the provider that served your request. Prices read 15:48 · speed over the last 30 minutes · uptime over 3 days.
One HTTP call, with your questions named as you like.
import os, requests
BASE = "https://opendunes.com"
KEY = os.environ["OPENDUNES_API_KEY"]
H = {"Authorization": f"Bearer {KEY}"}
resp = requests.post(f"{BASE}/alpha/decisions", headers=H, json={
"model": "respan/span-02",
"state": "The courier came two days late and the box was open.",
"questions": {
"is_complaint": {
"type": "noul",
"instructions": "Is it a complaint?",
"criteria": {
"true": "The customer is unhappy with the service.",
"false": "The customer is asking a question or saying thanks.",
},
},
},
})
print(resp.json())Runs this request once on your balance.
About 0,0033 DA per case. ↑ 3,33 DA per 1M tokens.
No. You pay per use from your balance, with no subscription. Run it once from Call it in code, at the same price.
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.
Deposit dinars with your Edahabia or CIB card. Every model, Span-02 included, is paid from that balance. No foreign card, no conversion.
Respan names no languages for Span-02. Arabic, French and Darja: not stated.
Yes or no, one choice from your list, or a score on your scale. Each answer comes with its probability.
Respan. Released 16 October 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.
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 7 Nov 2026.
Read a mixed text and image state and return one picked option per question you define
Take a long state of up to 131072 tokens and answer every question set against it
Judge an agent's output with a yes, no or unknown verdict before it reaches a user