by QwenReleased 13 August 2026
Qwen3 Reranker 8B reads a search question together with each candidate text and gives each pair a relevance score, so the best matches rise to the top. It covers over 100 languages and programming languages, and you can tell it what counts as relevant for your task. Use it as the second pass after a search step such as Qwen3's text-meaning models has fetched candidates, to put your answers in order. It does not write text itself.
You pay for what each request uses. No subscription, no minimum.
One search, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Text tokens | 66,57 DA |
per 1M tokens
One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send.
| Provider | Latency | Uptime |
|---|---|---|
| Fireworks | … | … |
You pay the price of the provider that served your request. Prices read 15:20 · speed over the last 30 minutes · uptime over 3 days.
One HTTP call. Any language that can send JSON can call it.
import os, requests
BASE = "https://opendunes.com/v1"
KEY = os.environ["OPENDUNES_API_KEY"]
H = {"Authorization": f"Bearer {KEY}"}
resp = requests.post(f"{BASE}/rerank", headers=H, json={
"model": "qwen/qwen3-reranker-8b",
"query": "Is the deposit refundable if I cancel?",
"documents": [
"A cancelled order refunds the deposit within 14 days.",
"Deposits are held for the life of the account.",
"Delivery outside Algiers takes three to five days.",
],
})
print(resp.json())Runs this request once on your balance.
About 0,067 DA per search. ↑ 66,57 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.
Qwen3 Reranker 8B reads a search question together with each candidate text and gives each pair a relevance score, so the best matches rise to the top. It covers over 100 languages and programming languages, and you can tell it what counts as relevant for your task. Use it as the second pass after a search step such as Qwen3's text-meaning models has fetched candidates, to put your answers in order. It does not write text itself.
Deposit dinars with your Edahabia or CIB card. Every model, Qwen3 Reranker 8B included, is paid from that balance. No foreign card, no conversion.
Qwen states support for over 100 languages, programming languages included, without listing them. Arabic, French and Darja are not named.
Up to 40 960 tokens for the query and one document together.
Qwen. Released 13 August 2026.
The 8B Qwen3 Embedding, carrying Qwen3's multilingual reach and long-text understanding into vectors for text and code retrieval, classification, clustering and bitext mining; the 4B is its smaller sibling
Qwen3 Embedding 4B turns text into a fingerprint of its meaning, so search finds text that means the same even in other words or another language. It covers over 100 languages, code included, and reads about 32 pages at once, which suits searching documents or code, grouping similar texts and matching translations.
Qwen-Audio-3.0-TTS Plus reads text and speaks it aloud, and Alibaba's docs say it takes plain-language directions for speech rate, emotion and speaking style. It is the higher-quality tier of the two Qwen-Audio-3.0 speech models, made by Alibaba. Pick it for narration, voiceover or any line where voice quality matters more than speed.
#6 for realistic voice · Qwen-Audio-3.0-TTS Flash reads text and speaks it aloud, and Alibaba's docs say it takes plain-language directions for speech rate, emotion and speaking style. It is the fast tier of the two Qwen-Audio-3.0 speech models, made by Alibaba. Pick it for volume work, such as many short lines, where response time matters more than the last bit of voice quality.
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 7 Nov 2026.
Open weights
The model's weights are public.
Reorder the top 50 search results for a question
Pick the three help-centre articles that best answer a ticket
Rank code snippets against a developer question