gpt-oss-20b

Name: OpenAI: gpt-oss-20b
Brand: OpenAI
Price: 9.99 DZD
Availability: InStock

by OpenAIReleased 5 August 2025

gpt-oss-20b reads text and writes text, keeping about 130 pages in mind at once. It is the smaller of OpenAI's two downloadable models, free to run yourself under an open license, quick enough to answer fast and light enough for an ordinary computer or a single graphics card. You choose how long it thinks, it can use the tools and apps you connect, and it can be retrained on your own examples.

TakesText

GivesText

Open in chat Create API key Compare

What it can do

From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 7 Nov 2026.

Strongest at

Top 10 %CheapestAmong 424 Text models
Top 10 %Writes the fastestAmong 424 Text models
#5Starts the soonestAmong 424 Text models

Yes or no

Thinks first
Works through the problem before it answers.
Uses your tools
Can call functions your code provides.
Fills your JSON
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.
Open weights
The model's weights are public.
Knows events up to 30 Jun 2024
What it learned stops at this date.

Jobs it takes on

Run a small agent that looks up orders through your API
Uses your tools
Pull fields from emails into JSON
Fills your JSON
Work through a short logic problem step by step
Thinks first

What it costs

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

≈ 0,032 DA per message3 000 DA buys about 94 000 messages

One message, the ordinary use

1 000 tokens sent× 9,99 DA per 1M0,010 DA

500 tokens back× 43,27 DA per 1M0,022 DA

Total≈ 0,032 DA

Every rate

Meter	↑ you send	↓ comes back
Text tokens	9,99 DA	43,27 DA
Cached tokens read	9,99 DA

per 1M tokens

Answer a quick question≈ 0,012 DA

Reply to a customer email≈ 0,023 DA

Classify 20 support tickets by topic≈ 0,029 DA

Translate a full page of text≈ 0,042 DA

Write a one-page draft≈ 0,042 DA

When you pay: After the answer, from your balance. Nothing is held.
Why it varies: A longer question or a longer answer costs more.
After each one: The exact charge shows on the request.

DepositDeposits from 50 DA, with Edahabia or CIB.

Where your request runs

Ten companies run this model. OpenDunes sends each request to one of them, picked by price and speed. If it fails, the next one takes it. DA per 1M tokens: ↑ what you send · ↓ what comes back.

PrimeIntellect…

↑ Sent, per 1M

1,33 DA

↓ Back, per 1M

5,66 DA

Cache read

1,00 DA

Latency

…

Throughput

…

Darkbloom…

↑ Sent, per 1M

5,99 DA

↓ Back, per 1M

29,96 DA

Cache read

3,00 DA

Latency

…

Throughput

…

AkashML…

↑ Sent, per 1M

6,66 DA

↓ Back, per 1M

33,28 DA

Cache read

none

Latency

…

Throughput

…

DekaLLMAsia…

↑ Sent, per 1M

9,65 DA

↓ Back, per 1M

46,60 DA

Cache read

9,65 DA

Latency

…

Throughput

…

CoreWeaveUnited States…

↑ Sent, per 1M

9,99 DA

↓ Back, per 1M

43,27 DA

Cache read

9,99 DA

Latency

…

Throughput

…

DeepInfraUnited States…

↑ Sent, per 1M

9,99 DA

↓ Back, per 1M

46,60 DA

Cache read

none

Latency

…

Throughput

…

Parasail…

↑ Sent, per 1M

9,99 DA

↓ Back, per 1M

49,93 DA

Cache read

6,66 DA

Latency

…

Throughput

…

SiliconFlowUnited States…

↑ Sent, per 1M

13,31 DA

↓ Back, per 1M

59,91 DA

Cache read

none

Latency

…

Throughput

…

Amazon BedrockEurope…

↑ Sent, per 1M

23,30 DA

↓ Back, per 1M

49,93 DA

Cache read

none

Latency

…

Throughput

…

Amazon Bedrock…

↑ Sent, per 1M

23,30 DA

↓ Back, per 1M

49,93 DA

Cache read

none

Latency

…

Throughput

…

Groq…

↑ Sent, per 1M

24,96 DA

↓ Back, per 1M

99,85 DA

Cache read

12,48 DA

Latency

…

Throughput

…

Provider	↑ Sent	↓ Back	Cache read	Latency	Throughput	Uptime
PrimeIntellect	1,33 DA	5,66 DA	1,00 DA	…	…	…
Darkbloom	5,99 DA	29,96 DA	3,00 DA	…	…	…
AkashML	6,66 DA	33,28 DA	none	…	…	…
DekaLLMAsia	9,65 DA	46,60 DA	9,65 DA	…	…	…
CoreWeaveUnited States	9,99 DA	43,27 DA	9,99 DA	…	…	…
DeepInfraUnited States	9,99 DA	46,60 DA	none	…	…	…
Parasail	9,99 DA	49,93 DA	6,66 DA	…	…	…
SiliconFlowUnited States	13,31 DA	59,91 DA	none	…	…	…
Amazon BedrockEurope	23,30 DA	49,93 DA	none	…	…	…
Amazon Bedrock	23,30 DA	49,93 DA	none	…	…	…
Groq	24,96 DA	99,85 DA	12,48 DA	…	…	…

You pay the price of the provider that served your request. Prices read 15:19 · speed over the last 30 minutes · uptime over 3 days.

See it in action

Real requests, real replies. Try any of them yourself — one click, pre-filled.

Structured output

You send

Turn this customer email into JSON with intent, urgency and order_id.

customer-email.txt

It replied

{ "intent": "refund", "urgency": "high", "order_id": "OD-58421" }

Try in Chat Lab

Writing

You send

Two lines to welcome a shop in Oran.

It replied

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 Lab

Try your own request — same model, pre-selected.

Open Chat Lab

Call it in code

Swap the base URL and the key. Your OpenAI code runs unchanged.

POST /v1/chat/completions

Base URL

https://opendunes.com/v1

Model ID

openai/gpt-oss-20b

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="openai/gpt-oss-20b",
    messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)

print(resp.choices[0].message.content)

pip install openaiFull reference for this route

Runs this request once on your balance.

Parameters you can send

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_ptop_kmin_pstopseedfrequency_penaltypresence_penaltyrepetition_penaltylogit_biaslogprobstop_logprobs

Reasoning

Let it think before answering — and see the thinking.

reasoningreasoning_effortinclude_reasoning

Structured output

Get JSON you can parse instead of prose.

response_formatstructured_outputs

Tools

Let the model call your functions.

toolstool_choice

Questions about gpt-oss-20b

How much does gpt-oss-20b cost in dinars?
About 0,032 DA per message. ↑ 9,99 DA · ↓ 43,27 DA per 1M tokens.
Is gpt-oss-20b free? Can I try it?
No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.
What is gpt-oss-20b best for?
gpt-oss-20b reads text and writes text, keeping about 130 pages in mind at once. It is the smaller of OpenAI's two downloadable models, free to run yourself under an open license, quick enough to answer fast and light enough for an ordinary computer or a single graphics card. You choose how long it thinks, it can use the tools and apps you connect, and it can be retrained on your own examples.
gpt-oss-20b or gpt-oss-safeguard-20b?
gpt-oss-safeguard-20b costs 0,043 DA more for the same message.
How do I pay for gpt-oss-20b without an international card?
Deposit dinars with your Edahabia or CIB card. Every model, gpt-oss-20b included, is paid from that balance. No foreign card, no conversion.
Does gpt-oss-20b work in Arabic, French or Darja?
OpenAI names no languages for gpt-oss-20b. Arabic, French and Darja: not stated.
Can it read PDFs, images or a whole book?
It reads text. Up to 131K tokens in one request, about 130 pages. It writes up to 88 000 words at once.
Is gpt-oss-20b open source?
Yes, its weights are public. Open weights on Hugging Face
Who makes gpt-oss-20b, and when was it released?
OpenAI. Released 5 August 2025. It knows the world up to 30 June 2024.

Other OpenAI models, priced in dinars

See all OpenAI models

Text Embedding 3 SmallOpenAI · Oct 30, 2025

Text Embedding 3 Small turns text of up to about 8 pages into a fingerprint of its meaning, so search finds passages that mean the same thing even when the words differ. It replaces the older ada-002 and is the sensible default for search over your documents, grouping similar messages or labelling them.

8 pages per call

≈0,0067 DAper page

View model

GPT Image 2.5 SunburstOpenAI · Sep 9, 2026

GPT Image 2.5 Sunburst takes a written description, with optional reference pictures, and gives back an image, new or edited, as PNG, JPEG or WebP, with transparent backgrounds on PNG and WebP. It is the precision tier of the 2.5 series, for detailed creative work where an edit has to land exactly as asked, and it adds top quality settings named xhigh and max.

Up to 16 referencesTransparent background

≈4,38 DAper image

View model

GPT-6 Luna DecisionsOpenAI · Oct 6, 2026

GPT-6 Luna Decisions does not write text. You send content as text, a table of data or a picture, plus up to 200 named questions of three kinds: yes or no, pick among options, or grade against an ordered scale. It returns a probability for every answer, with the likeliest option or expected score, so your own system can set its thresholds for routing, moderation or marking.

1 050 pages per call

≈0,033 DAper case

View model

Text Embedding 3 LargeOpenAI · Oct 30, 2025

Text Embedding 3 Large turns text of up to about 8 pages into a fingerprint of its meaning, so search finds passages that mean the same thing even when the words differ. It is the most accurate of OpenAI's models of this kind, in English and other languages. Choose it when the quality of matches matters most, for search, grouping or labelling documents.

8 pages per call

≈0,043 DAper page

View model

gpt-oss-20b

What it can do

Strongest at

Yes or no

Jobs it takes on

What it costs

Where your request runs

See it in action

Call it in code

Parameters you can send

Questions about gpt-oss-20b

How much does gpt-oss-20b cost in dinars?

Is gpt-oss-20b free? Can I try it?

What is gpt-oss-20b best for?

gpt-oss-20b or gpt-oss-safeguard-20b?

How do I pay for gpt-oss-20b without an international card?

Does gpt-oss-20b work in Arabic, French or Darja?

Can it read PDFs, images or a whole book?

Is gpt-oss-20b open source?

Who makes gpt-oss-20b, and when was it released?

Other OpenAI models, priced in dinars

What it can do

Strongest at

Yes or no

Jobs it takes on