gpt-oss-20b

apache-2.020B

`gpt-oss-20b` is our medium-sized open-weight model for low latency, local, or specialized use-cases (21B parameters with 3.6B 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-20b-1:0
Provider Amazon Bedrock
Creator OpenAI
Familygpt-oss
Licenseapache-2.0
Statusactive
Typechat
Input modalitiestext
Output modalitiestext
Open weight—
Parameters20B
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-20b-1:0

gpt-oss-20b

openai.gpt-oss-20b-1:0

`gpt-oss-20b` is our medium-sized open-weight model for low latency, local, or specialized use-cases (21B parameters with 3.6B active parameters).

Changes · 6 entries
openai.gpt-oss-20b-1:0updateca7a400Nov 2, 2026, 03:02 AM
capabilitiesreasoningyes
release_date2025-08-05
context_window128000
max_output_tokens16000
page_urlhttps://docs.aws.amazon.com/bedrock/latest/userguide/mode...
reasoning_tokensyes
openai.gpt-oss-20b-1:0updatebcf2693Oct 16, 2026, 06:36 AM
reasoning_tokensyes
openai.gpt-oss-20b-1:0update80c574aJun 3, 2026, 07:05 AM
release_date2025-08-05
context_window128000
max_output_tokens16000
page_urlhttps://docs.aws.amazon.com/bedrock/latest/userguide/mode...
openai.gpt-oss-20b-1:0update2b100acMar 23, 2026, 05:30 AM
familygpt-oss
parameters20
openai.gpt-oss-20b-1:0update7a4f1f6Mar 22, 2026, 05:43 AM
model_typechat
openai.gpt-oss-20b-1:0create7f5c66fMar 21, 2026, 05:16 AM