by ThenlperReleased 18 November 2025
GTE-Large turns English text into a fingerprint of its meaning, so a search finds writing that means the same thing even when the words differ. It also groups similar texts together, and it reads about half a page at a time, cutting off anything longer. It is the larger and higher-scoring of the two sizes.
You pay for what each request uses. No subscription, no minimum.
One page, 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.
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.
Swap 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.embeddings.create(
model="thenlper/gte-large",
input="Delivery to Oran takes two days.",
)
print(resp.data[0].embedding[:5])Runs this request once on your balance.
About 0,0033 DA per page. ↑ 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.
GTE-Large turns English text into a fingerprint of its meaning, so a search finds writing that means the same thing even when the words differ. It also groups similar texts together, and it reads about half a page at a time, cutting off anything longer. It is the larger and higher-scoring of the two sizes.
Deposit dinars with your Edahabia or CIB card. Every model, GTE-Large included, is paid from that balance. No foreign card, no conversion.
The model card says it works only on English text. Arabic, French and Darja are not supported.
Up to 512 tokens. Split anything longer.
1 024
Thenlper. Released 18 November 2025.
GTE-Base turns English text into a fingerprint of its meaning, so a search finds writing that means the same thing even when the words differ. It also groups similar texts together, and it reads about half a page at a time, cutting off anything longer. GTE-Large scores a little higher in the maker's own tests.
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.
Index your help centre for semantic search
Find duplicate support tickets
Match product titles across two catalogues