OpenAItext->text

OpenAI: gpt-oss-120b

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.

Context Window

131K

Input Price

$0.0400/M tokens

Output Price

$0.1900/M tokens

Modality

text->text

Pricing Breakdown

Cost per million tokens for input and output

Input$0.0400/M tokens

Output$0.1900/M tokens

Cost Example: Processing 10,000 input tokens and generating 1,000 output tokens would cost approximately $0.000590

Context Window Size

Maximum tokens the model can process in a single request

Context Window131K tokens

13% of 1M max

~98K

Words Equivalent

~66

Pages of Text

~1311

Code Functions

Best Use Cases

What this model excels at

MathReasoningAnalysis

Related Categories:

Data Analysis

Test OpenAI: gpt-oss-120b Now

Compare this model with others using your own prompts

Ready to Test OpenAI: gpt-oss-120b?

Use our free AI Models Tester to compare OpenAI: gpt-oss-120b with other models side-by-side using your own prompts. See real results instantly.