OpenAI

Ogpt-oss-20b (free)OPEN

gpt-oss-20b (free) (OpenAI): live API pricing, context window and the best open-source alternatives, tracked daily by olud.ai.

Context window
131K
tokens
Input price
Free
per M tokens
Output price
Free
per M tokens
Provider
OpenAI

Prices update automatically — checked hourly against provider list prices.

See model comparisons → Compare all model prices

Benchmarks & performance

Independent benchmark scores for gpt-oss-20b (free), measured by Artificial Analysis. Higher is better. Measurement mode: high.

26×
More intelligence per dollar than Claude Opus 5 (Fast).
For the same budget, gpt-oss-20b (free) delivers 26 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Intelligence index14.9
Coding index20.7
Math index89.3
GPQA68.8%
MMLU-Pro74.8%
Humanity's Last Exam9.8%
Long Context Reasoning30.7%
LiveCodeBench77.7%
SciCode34.4%
AIME 202589.3%
IFBench65.1%
τ²-Bench60.2%
τ-Bench Banking7%
Terminal-Bench13.9%
Terminal-Bench Hard10.6%
⚡ Speed167.5 tokens/sec
⏱ Latency0.47s to first token
💰 Blended price$0.095 / 1M tokens
📈 Value156.8 intelligence points per $
Benchmark data by Artificial Analysis

About this model

gpt-oss-20b (free) 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 hourly, for when you prefer convenience over self-hosting.

Frequently asked questions

What is gpt-oss-20b (free)?

gpt-oss-20b (free) is an AI language model from OpenAI. It is open-weight: you can download it and run it on your own hardware, for free. It scores 14.9 on the Artificial Analysis intelligence index.

Is gpt-oss-20b (free) free?

The weights are free and open — you can self-host gpt-oss-20b (free) and pay nothing per token. If you prefer a hosted API, list prices are Free per million input tokens and Free per million output tokens.

What is gpt-oss-20b (free) good at?

Independent benchmarks from Artificial Analysis give it GPQA 68.8%, MMLU-Pro 74.8%, Humanity's Last Exam 9.8%, Long Context Reasoning 30.7%, LiveCodeBench 77.7%, SciCode 34.4%, AIME 2025 89.3%, IFBench 65.1%, τ²-Bench 60.2%, τ-Bench Banking 7%, Terminal-Bench 13.9%, Terminal-Bench Hard 10.6%. It is particularly used for code generation.

How fast is gpt-oss-20b (free)?

It generates about 167.5 tokens per second, with a median 0.47s delay before the first token. Measured independently by Artificial Analysis.

Can I self-host gpt-oss-20b (free)?

Yes. gpt-oss-20b (free) 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.

Related models

o1-proOpenAIGPT-5.5 ProOpenAIGPT-5.4 ProOpenAIGPT-5.2 ProOpenAIGPT-5 ProOpenAIo3 ProOpenAI