GPT-OSS 20B · OpenAI
GPT-OSS 20B is the compact version of the open-weights model from OpenAI. Very fast (~3× the speed of the 120B) with solid quality for non-critical tasks.
About GPT-OSS 20B
GPT-OSS 20B is the compact version of the open-weights model from OpenAI. Very fast (~3× the speed of the 120B) with solid quality for non-critical tasks.
Where it shines: Ultra-fast · OpenAI quality · Open-weights.
How to use GPT-OSS 20B
-
1
Type or upload
Type what you want in the box above — or upload the file if the tool asks for one.
-
2
Generate
Click the main button. Wait 2-30 seconds depending on the model and input size.
-
3
Download or share
Download the result or share the direct link. No watermark, ready to use.
Frequently asked questions
How much does it cost to use GPT-OSS 20B?
GPT-OSS 20B is a Pro model: it costs 10 tokens per use (~$0.05 real cost for us). You need a Pro plan ($9/month → 15,000 tokens) or a one-shot pack. If you already have tokens in the free account, you can also spend them directly.
How many uses of GPT-OSS 20B are included in the Pro plan?
Pro ($9/month) gives you 15,000 recurring tokens. At 10 tokens per use of GPT-OSS 20B, that's ~1,500 full uses per cycle. If you run out, one-shot packs (5,000 / 25,000 / 80,000 tokens) add to the balance without expiring before one year.
What makes GPT-OSS 20B special?
OpenAI is the lab behind ChatGPT; its models have broad world knowledge and polished outputs, its specific strengths are: ultra-fast, openai quality and open-weights.
How fast does GPT-OSS 20B respond?
GPT-OSS 20B is one of the fastest models in the catalog: typical responses in 2-5 seconds, the actual time also depends on the length of the prompt and the load of the datacenter — models with huge context take longer when you enter very long texts.
How do I use GPT-OSS 20B in ia.gratis?
You can use GPT-OSS 20B from /chat/ by selecting GPT-OSS 20B in the picker, or via the REST API with `model=gpt-oss-20b` in the body of the POST. Quick summary: small and fast open gPT.The internal model identifier is `gpt-oss-20b` — useful when integrating via API.