by UnbiasedReleased 13 October 2026
A multimodal composite model for research, coding and agentic work that runs several models on each request without switching mid-conversation, reads text and images in a 262,144-token window and calls your tools
You pay for what each request uses. No subscription, no minimum.
One message, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Text tokens | 832,09 DA | 2 496,27 DA |
| Cached tokens read | 83,21 DA |
per 1M tokens
One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send · ↓ what comes back.
| Provider | ↑ Sent | ↓ Back | Cache read | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|
| Unbiased | 832,09 DA | 2 496,27 DA | 83,21 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.
Real requests, real replies. Try any of them yourself — one click, pre-filled.
What's the total on this invoice, and when is it due?
invoice-scan.jpg · photoThe total is 42 300,00 DA, due 5 September 2026. Worth a double-check: the handwritten day could read as 8 instead of 3.
Try in Chat LabTwo lines to welcome a shop in Oran.
Welcome to our new shop in Oran — fresh bread every morning, and coffee the way the city likes it. Come in, the first cup is on us.
Try in Chat LabTry your own request — same model, pre-selected.
Open Chat LabSwap the base URL and the key. Your OpenAI code runs unchanged.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://opendunes.com/v1",
api_key=os.environ["OPENDUNES_API_KEY"],
)
resp = client.chat.completions.create(
model="unbiased/pareto-26.9",
messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)
print(resp.choices[0].message.content)Runs this request once on your balance.
Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.
Shaping the reply
How long, how varied, where to stop.
max_tokenstemperaturetop_pStructured output
Get JSON you can parse instead of prose.
response_formatTools
Let the model call your functions.
toolstool_choiceAbout 2,08 DA per message. ↑ 832,09 DA · ↓ 2 496,27 DA per 1M tokens.
No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.
A multimodal composite model for research, coding and agentic work that runs several models on each request without switching mid-conversation, reads text and images in a 262,144-token window and calls your tools.
Deposit dinars with your Edahabia or CIB card. Every model, Pareto 26.9 included, is paid from that balance. No foreign card, no conversion.
Unbiased names no languages for Pareto 26.9. Arabic, French and Darja: not stated.
It reads text and images. Up to 262K tokens in one request, about 260 pages. It writes up to 98 000 words at once.
No. Unbiased has not published its weights.
Unbiased. Released 13 October 2026.
Pareto 26.10 is a multimodal composite model for research, coding and agentic workflows that reads text and images, calls your tools and holds a million tokens in view, with frontier-level performance on general-purpose tasks
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 7 Nov 2026.
Thinks first No.
Works through the problem before it answers.
Uses your tools
Can call functions your code provides.
Fills your JSON No.
Answers in the JSON shape you give it.
Searches the web No.
Can look things up online while it answers.
Cheaper on repeats
A prompt it saw a moment ago costs less the second time.
Runs multi-step agent work by invoking your tools across long briefs
Uses your tools
Writes a single answer of up to 131,072 tokens, enough for a full-length report
Reads screenshots beside text to explain charts, interfaces, and documents