Strengths
- OpenAI says it runs on devices with 16 GB of memory and scores similarly to o3-mini on common tests.
- The Apache 2.0 license allows commercial use and changes to the model.
- You can set thinking to low, medium or high and see the full chain of reasoning.
- When it runs on your own computer, your text goes nowhere and it works offline.
Weaknesses
- Knowledge stops in June 2024, it only understands text and its context window is 131K tokens.
- Trained mostly on English text, so expect weaker results in Slovak and Czech.
- OpenAI does not list it in its API price list, so you run it yourself or through another provider.
Best for
- a private offline assistant on your computer
- experiments with sensitive data
- quick specialised tasks
Not ideal for
- complex multi-step work
- up-to-date information
How to use it in Europe
It is unclear whether the OpenAI API still serves it: OpenAI lists no price and the model page shows zero rate limits. You can download the weights for free from Hugging Face and run them on your own computer or server, or use a provider that hosts it. The license has no geographic limits. When it runs on your own machine, your data goes nowhere, which is the safest option for privacy.
More models from this vendor
- GPT-6 Astra: OpenAI's most capable model, built for the hardest coding, agents that operate a computer and very long documents.
- GPT-6.1 Sol: OpenAI's balanced model, close to GPT-6 Astra in quality at a fifth of the price. A solid pick for business apps.
- GPT-6.1 Terra: OpenAI's fast, cheaper model for working with images, operating a computer and everyday office work.
- GPT-6 Luna: OpenAI's cheapest model, made for high volumes of simple tasks, sorting text and low-cost chatbots.
- gpt-oss-120b: OpenAI's open model that a company can run on its own server when data must not leave its infrastructure.
Similar models from other vendors
- Gemma 4 31B (Google): Google's largest open model, which you can run on your own computer or server when data must not leave the company.
- Gemma 4 26B A4B (Google): Google's faster open model for your own server. Close to the larger Gemma 4 31B in quality, but quicker to respond.
- Muse Glimmer 30B (Meta): Meta's small open model under Apache 2.0 that runs on a single graphics card, even offline.
- Llama 4 Scout (Meta): The smaller Llama 4 from April 2025, very cheap through providers. Its license grants no rights to people or companies in the EU.
- Ministral 3 14B (Mistral AI): Mistral's small open model under Apache 2.0 that runs on a single GPU, even without an internet connection.
- Nemotron 3.5 Bolt 74B-A9B (NVIDIA): NVIDIA's open model for AI agents on your own powerful PC, small enough to fit in 24 GB of graphics card memory.