O
gpt-oss-20bOPEN
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.
Prices update automatically — checked daily against provider list prices.
- $0.04 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 90% of the 200 open-weight models tracked here
- 1 of 101 OpenAI models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for gpt-oss-20b, measured by Artificial Analysis. Higher is better. Measurement mode: Low.
About this model
gpt-oss-20b is an open-weight AI model by OpenAI. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.
Frequently asked questions
What is gpt-oss-20b?
gpt-oss-20b is an AI language model from OpenAI. It is open-weight: you can download it and run it on your own hardware, for free.
Is gpt-oss-20b free?
The weights are free and open — you can self-host gpt-oss-20b and pay nothing per token. If you prefer a hosted API, list prices are $0.02 per million input tokens and $0.09 per million output tokens.
What is gpt-oss-20b good at?
Independent benchmarks from Artificial Analysis give it GPQA 61.1%, MMLU-Pro 71.8%, Humanity's Last Exam 5.3%, Long Context Reasoning 31%, LiveCodeBench 65.2%, AIME 2025 62.3%, IFBench 57.8%, τ²-Bench 50.3%, Terminal-Bench Hard 4.5%. It is particularly used for mathematical reasoning.
How fast is gpt-oss-20b?
It generates about 214.3 tokens per second, with a median 0.49s delay before the first token. Measured independently by Artificial Analysis.
Can I self-host gpt-oss-20b?
Yes. gpt-oss-20b has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.