gpt-oss-120b
gpt-oss-120b is OpenAI's larger open-weight model (Apache 2.0, August 2025): mixture-of-experts, 117B parameters with 5.1B active per token. OpenAI positions it for production, general-purpose work that needs strong reasoning, with function calling, structured outputs and three levels of reasoning effort. It gives you an OpenAI-trained model without an OpenAI contract — same key and invoice as the rest of this catalog. It is served by a third-party inference provider through our partner, not on Heabsy hardware: the same key and the same invoice, but no zero data retention, and the request may be processed outside the EEA.
model id: gpt-oss-120b
from openai import OpenAI client = OpenAI( api_key="hb-...", base_url="https://api.heabsy.com/v1",) r = client.chat.completions.create( model="gpt-oss-120b", messages=[{"role": "user", "content": "Hello"}],)print(r.choices[0].message.content)
curl https://api.heabsy.com/v1/chat/completions \ -H "Authorization: Bearer $HEABSY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-oss-120b", "messages": [{"role": "user", "content": "Hello"}] }'
import OpenAI from "openai"; const client = new OpenAI({ apiKey: process.env.HEABSY_API_KEY, baseURL: "https://api.heabsy.com/v1",}); const r = await client.chat.completions.create({ model: "gpt-oss-120b", messages: [{ role: "user", content: "Hello" }],});console.log(r.choices[0].message.content);
Use it in Claude Code · OpenCode · Cline · Kilo Code · SillyTavern · n8n
Price list, updated 21 October 2026. No minimum spend, no subscription.
About the model
- Developer
- OpenAI
- Released
- August 2025
- Licence
- Apache-2.0
- Architecture
- mixture of experts · 117B parameters, 5.1B active per token
- Input
- text
- Reasoning
- selectable effort
- Knowledge cutoff
- June 2024
- Languages named by the developer
- none named on the model card
Source: the developer's model card, as of 17 September 2026.
gpt-oss-120b is not GPT-6
gpt-oss-120b is OpenAI's open-weight model from August 2025 under Apache 2.0: text only, with three reasoning levels (low, medium, high). It is not one of the models behind ChatGPT. The GPT-6 and GPT-5.6 models in this catalogue are OpenAI's closed models — a different family.
It has 117B parameters with 5.1B active per token and is aimed at production reasoning. Its smaller sibling gpt-oss-20b (21B, 3.6B active, fits into 16 GB of memory) is not in this catalogue.
OpenAI does not list supported languages but measured 14 of them on the multilingual MMMLU test (at high reasoning effort, German: 83.0). OpenAI gives a knowledge cutoff of June 2024. If you run the weights yourself, the card requires OpenAI's harmony response format; through our API you use the ordinary chat completions call shown above.
Licence: what it means for your company
Apache-2.0. A permissive open-source licence: you may use, modify and sell products built on the model, including commercially; when you redistribute the weights, the licence and copyright notices go with them.
A summary of the licence, not legal advice.
Benchmarks reported by the developer
- AIME 2025
- 92.5 %
- GPQA Diamond
- 80.1 %
- MMLU
- 90 %
- SWE-bench Verified
- 62.4 %
Figures from the developer's model card, not our measurement. Source: arxiv.org/abs/2508.10925
Technical details
- Context window
- 125K tokens
- Max output
- 16,384 tokens
- Throughput limit
- —
- Tokenizer
- Other
- Streaming
- yes
- Open weights
- —
- max_tokens
- 1 … 16384
This model is served by a third-party inference provider through our partner, not on Heabsy hardware. You keep one key and one invoice from an EU company, but there is no zero data retention: the provider handles the request under its own policy, and processing may take place outside the EEA. For personal or regulated data, use a model on Heabsy hardware.
Questions about this model
›Where is gpt-oss-120b computed?
At a third-party inference provider that serves this model through our partner, outside our own infrastructure. Where exactly the request is computed is not fixed and may be outside the EEA. The contract and the invoice stay with our EU company.
›Does gpt-oss-120b store prompts and completions?
There is no zero-data-retention guarantee for this model: the request goes to a third-party provider, which handles it under its own policy and may keep logs. For personal or regulated data, use a model on Heabsy hardware.
›How large is the gpt-oss-120b context window?
125K tokens, with up to 16,384 tokens of output.
›What does gpt-oss-120b cost?
$0.70 per million input tokens and $1.50 per million output tokens. No minimum spend and no subscription; the same price list covers the API and the invoice.
›Is there a throughput limit on gpt-oss-120b?
The catalog does not report a throughput limit for this model.
›Which languages does gpt-oss-120b support?
The developer's model card names no languages. Test the model on your own material before relying on it in a particular language. OpenAI did measure 14 languages on the multilingual MMMLU test, German among them.
›Under which licence is gpt-oss-120b released?
Apache-2.0. A permissive open-source licence: you may use, modify and sell products built on the model, including commercially; when you redistribute the weights, the licence and copyright notices go with them.
›Can reasoning be switched off in gpt-oss-120b?
The developer lets you choose how much the model reasons; the card does not document turning reasoning off completely.
Compare with similar models
| Model | Developer | Parameters | Context | Licence | Input / 1M |
|---|---|---|---|---|---|
| gpt-oss-120b | OpenAI | 117B / 5.1B | 125K | Apache-2.0 | $0.70 |
| GPT-6 Luna | OpenAI | — | 1M | — | $0.12 |
| GPT-5.6 Luna | OpenAI | — | 1M | — | $0.24 |
| GPT-5.6 Sol | OpenAI | — | 1M | — | $2.40 |
35 more models behind the same key and the same invoice.
Browse the catalog