Model Platform
Hot
Wan2.6
NEW
Seedream v4.5
Wan 2.5
Wan 2.2
Sora 2
Nano Banana Pro
Image & Video Models
Kling o1
Veo 3.1
Hailuo 2.3
Seedance
Seedream v4.0
Ltx-2
Flux.2
Flux Kontext
Large Language
DeepSeek
OpenAI
Anthropic
Gemini
Grok
Qwen
Moonshot
Z.ai
Doubao
MiniMax
View all models
Agent Solutions
GPU Cloud
On-Demand GPUs
Bare Metal
Serverless
Pricing
Pay by Usage
Pay by GPU/hr
Developers
Docs
Blog
Company
News & Events
About Us
Contact
Contact
Contact
Model Platform
Image & Video Models
Create and scale visual imagination.
Large Language Models
Power intelligent reasoning and conversation.
Serverless
Deploy, customize, and build with Dedicated Endpoint, Fine-Tuning, and DevPod.
Agent Solutions
GPU Cloud
On-Demand GPUs
Scale AI workloads with high-performance cloud GPUs.
Bare Metal
Run AI models faster on dedicated GPU servers.
Pricing
Pay by Usage
Pay by GPU/hr
Developers
Docs
Blog
Company
News & Events
About Us
Contact
openai/gpt-oss-120b
117B-parameter MoE language model from OpenAI.
LLM
FP8
NEW
Home
Explore
Open AI Model Families
OpenAI LLM Models
openai/gpt-oss-120b
LLM
openai/gpt-oss-120b
Gpt-oss-120b
117B-parameter MoE language model from OpenAI.
Add to favourite
Loading...
All You Need to Know About This Model
Overview:
Model Provider:
OPENAI
Model Type:
Large Language Model
Deployment:
Inferencing API; Playground
Pricing:
$0.1/M Input & $0.2/M Output
Key Specs:
Parameters:
116.8B total; ~5.1B active
Context:
131k tokens
Architecture Type:
Mixture-of-Experts (MoE)
Knowledge Cutoff:
June 2024
Core Strengths:
Open-source availability and access
Large 120B parameter scale
Full model transparency
Community-driven development approach
Use Cases:
Research application development
Custom deployment solutions
Educational tool creation
Specialized model fine-tuning
Start From 300+ Models,
Only at Atlas Cloud.
Explore all models