OpenAI Models
OpenAI logo

gpt-oss-20b

20B

by OpenAI

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.

Chat with gpt-oss-20b
Input Price$0.07/1M tokens
Output Price$0.23/1M tokens
Intelligence24.5
Coding18.5

Specifications

Technical details and pricing.

ProviderOpenAI
Context Window131,072 tokens
Release DateAug 5, 2025
ModalitiesText

Benchmarks

10 benchmark scores from Artificial Analysis.

GPQA68.8%
MMLU Pro74.8%
HLE9.8%
LiveCodeBench77.7%
AIME 202589.3%
SciCode34.4%
LCR30.7%
IFBench65.1%
Tau260.2%
TerminalBench Hard10.6%

Composite Indices

Intelligence, Coding, Math

Standard Benchmarks

Academic and industry benchmarks

Frequently Asked Questions

What is gpt-oss-20b good for?

Use gpt-oss-20b for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does gpt-oss-20b cost?

Pricing is based on usage. Current rates are $0.07/1M tokens for input and $0.23/1M tokens for output.

Can I try gpt-oss-20b for free?

Yes. You can start a chat instantly and test the model before deciding on a plan.

Does gpt-oss-20b support images or audio?

gpt-oss-20b focuses on text-based tasks.

Benchmarks and pricing are sourced from Artificial Analysis where available. OpenRouter specs are used as a fallback.