OpenAI Models
OpenAI logo

gpt-oss-120b

120B

by OpenAI

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

Chat with gpt-oss-120b
Input Price$0.15/1M tokens
Output Price$0.60/1M tokens
Intelligence33.3
Coding28.6

Specifications

Technical details and pricing.

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

Benchmarks

10 benchmark scores from Artificial Analysis.

GPQA78.2%
MMLU Pro80.8%
HLE18.5%
LiveCodeBench87.8%
AIME 202593.4%
SciCode38.9%
LCR50.7%
IFBench69.0%
Tau265.8%
TerminalBench Hard23.5%

Composite Indices

Intelligence, Coding, Math

Standard Benchmarks

Academic and industry benchmarks

Frequently Asked Questions

What is gpt-oss-120b good for?

Use gpt-oss-120b for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does gpt-oss-120b cost?

Pricing is based on usage. Current rates are $0.15/1M tokens for input and $0.60/1M tokens for output.

Can I try gpt-oss-120b for free?

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

Does gpt-oss-120b support images or audio?

gpt-oss-120b focuses on text-based tasks.

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