gpt-oss-120b
Rank #21
openai
openai/gpt-oss-120b
Usage data date 2026-07-26 · updated daily
Usage and specs
Daily rank#21
Daily tokens470B
Daily requests115.5M
Daily change
−11.1%
Context window131.1K
Released
What is 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.
gpt-oss-120b capabilities
Input: Text Output: Text
gpt-oss-120b API pricing
Input · per 1M tokens$0.04
Output · per 1M tokens$0.17
List prices in USD; see each provider’s site for current terms.
Tools built on this model
ChatGPT
Best for people or teams exploring chat and assistance; not suitable for high-risk decisions without human review and current official terms.
GPT-4
Best for people or teams exploring model training and use; not suitable for high-risk decisions without human review and current official terms.
DALL·E 3
Best for people or teams exploring model training and use; not suitable for high-risk decisions without human review and current official terms.
Codex
Best for professional developers and engineering teams that want to delegate development, refactoring, and ops work to an AI agent; not for non-programmers or users who only need simple code completion.
StudyCorgi ChatGPT Detector
Suitable for students and teachers who need a free, fast way to screen essays and assignments; not suitable for users who must scan very long documents or batches of files.