GPT-OSS-120B

Model mdl-7x9a2f

Back to Models
TU

GPT-OSS-120B

Deployed

Open-weight frontier-scale language model for advanced reasoning, coding, and long-context enterprise workloads

LanguageCode
Deployed on Nexus CloudView Deployment →
Created

Feb 18, 2026

Parameters

120B

Accuracy

97.2%

Training Time

18h 40m

Data Sources

Production Corpus

s3://trinidy-training/corpus-v3

2.5M records

Azure Telemetry Store

https://trinidydata.blob.core.windows.net/telemetry

5.1M records

Inference Endpoint

Endpoint URI

https://nexus.trinidy.cloud/v1/gpt-oss-120b/inference

Region

us-east-1

Instance

nexus.gpu.a100

Replicas

3/8

Uptime

99.98%