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.

Reasoning

Speed

Context

131K

Max output

131K

Input price

—

Output price

—

Capabilities

vision

tool call

structured output

reasoning

json mode

streaming

fine tuning

batch

Details

ProviderOpenAI

CreatorOpenAI

Familygpt-oss

Statusactive

Input modalitiestext

Output modalitiestext

Knowledge cutoff—

Release date—

Deprecation date—

Sourceofficial

Last updated2026-03-20

Max input—

gpt-oss family

Model	Perf	Speed	Context	Max out	Input	Output
gpt-oss-120bRT			131K	131K	—	—
gpt-oss-20bRT			131K	131K	—	—

API

GET/v1/models/openai/gpt-oss-120b