gpt-oss-120b

reasoning

Intelligence

Reasoning

Speed

Context

131K

Max output

131K

Capabilities

vision

tool call

structured output

reasoning

json mode

streaming

fine tuning

batch

Details

ProviderOpenAI

CreatorOpenAI

Familygpt-oss

Statusactive

Input modalitiestext

Output modalitiestext

Knowledge cutoff2024-05

Release date—

Deprecation date—

Typereasoning

Reasoning tokensYes

Max input—

Sourceofficial

Last updated2026-03-21

Tools

Function Callingfunction_calling

Call external functions and APIs

Code Interpretercode_interpreter

Execute code in a sandbox

MCPmcp

Connect to Model Context Protocol servers

Web Searchweb_search

Search the web for information

Endpoints

ResponsesPOST

Stateful multi-turn conversationshttps://api.openai.com/v1/responses

BatchPOST

Async batch processing at lower costhttps://api.openai.com/v1/batches

Family Comparison: gpt-oss

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

API

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

gpt-oss-120b

Changes · 2 entries

gpt-oss-120bupdateb50649fMar 21, 2026, 11:58 PM

descriptiongpt-oss-120b is an open-weight, 117B-parameter Mixture-of...→\

capabilitiesstreamingyes

knowledge_cutoff2024-05

model_typereasoning

reasoning_tokensyes

reasoning4

taglineMost powerful open-weight model, fits into an H100 GPU

tools["function_calling","code_interpreter","mcp","web_search"]

endpoints["responses","batch"]

snapshots["gpt-oss-120b"]

gpt-oss-120bcreate7f5c66fMar 21, 2026, 05:16 AM