gpt-oss-120b

by OpenAI

gpt-oss-120b is OpenAI's open-weight mixture-of-experts model, with 117B parameters and 5.1B active per token, released under Apache 2.0. It reasons with adjustable effort (low, medium, or high), calls tools, and has a 131,072-token context window. We serve the original MXFP4 weights, with no further quantization, from a dedicated GPU in the US.

Best for: Low-cost reasoning, extraction, and tool use over long text.

131K context

Text
Reasoning
Tool use

Model weights

Try it in the playground

Pricing

USD per 1M tokens.

Provider	Input	Cached input	Output
Boundless	$0.095	$0.095	$0.475

What one request costs

Prompt12Ktokens

Cached prefix8Ktokens

Reply2Ktokens

$0.0019

per request to gpt-oss-120b

Prompt: 18.5%
Cached: 43.1%
Reply: 38.5%

The same request, across other models