gpt-oss-120b

apache-2.0120B

`gpt-oss-120b`is our most powerful open-weight model, which fits into a single H100 GPU (117B parameters with 5.1B active parameters).

Intelligence
Reasoning
Speed
Context
128K
Max output
16K

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming
Batch Processing

Details

Model IDopenai.gpt-oss-120b-1:0
Provider Amazon Bedrock
Creator OpenAI
Familygpt-oss
Licenseapache-2.0
Statusactive
Typechat
Input modalitiestext
Output modalitiestext
Open weight—
Parameters120B
Architecture—
Context window128K tokens
Max input—
Max output16K tokens
Reasoning tokensYes
Knowledge cutoff
Release date
Sourceofficial

Family Comparison: gpt-oss

ModelContextMax out
gpt-oss-120b128K16K
gpt-oss-20b128K16K

API

GET/v1/models/amazon/openai.gpt-oss-120b-1:0