opendunes

Span-01

by RespanReleased 26 September 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.

TakesText
GivesClassification

Where your request runs

One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send.

Respan…
↑ Sent, per 1M
6,66 DA
Latency
…
Provider↑ SentLatencyUptime
Respan6,66 DA……

You pay the price of the provider that served your request. Prices read 02:48 · speed over the last 30 minutes · uptime over 3 days.

What it costs

You pay for what each request uses. No subscription, no minimum.

≈ 0,0067 DA per case3 000 DA buys about 450 000 cases

One case, the ordinary use

1 000 sent1 000 tokens sent× 6,66 per 1M× 6,66 DA per 1M0,0067 DA
Total≈ 0,0067 DA

Every rate

Meter↑ you send↓ comes back
Text tokens6,66 DA

per 1M tokens

Everyday jobs, priced

Screen one user message for prompt injection≈ 0,0013 DA
Score one support chat for escalation≈ 0,010 DA
Check one agent trace for five behaviours≈ 0,027 DA
Check a long agent run for loops≈ 0,080 DA
Score 100 chats for frustration≈ 1,00 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
The length of the text.
After each one
The exact charge shows on the request.
Add creditDeposits from 100 DA, withEdahabiaCIB

Call it in code

One HTTP call, with your questions named as you like.

POST /alpha/decisions
Base URL
https://opendunes.com/v1
Model ID
respan/span-01
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-01",
    "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())
pip install requestsFull reference for this route

Runs this request once on your balance.

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

How much does Span-01 cost in dinars?

About 0,0067 DA per case. ↑ 6,66 DA per 1M tokens.

Is Span-01 free? Can I try it?

No. You pay per use from your balance in dinars, with no subscription. The chat has free models for free messages every day.

What is Span-01 best for?

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.

How do I pay for Span-01 without an international card?

Add credit in dinars with your Edahabia or CIB card. Every model, Span-01 included, is paid from that balance. No foreign card, no conversion.

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

Respan names no languages for Span-01. 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, 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