openai/gpt-oss-20b

Welcome to the gpt-oss series, OpenAI's open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. gpt-oss-20b is a 21.5B parameter model with Mixture-of-Experts (MoE) architecture, featuring 3.6B active parameters during inference. It's optimized for lower latency and local or specialized use-cases, supporting configurable reasoning depth for agentic applications.

OpenAI Chat 131.1k Tokens
Get API Key
Try in Playground
Free Trial Credit No Credit Card Required
$1.00

api_example.sh

curl -X POST "https://platform.qubrid.com/v1/chat/completions" \
  -H "Authorization: Bearer QUBRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "openai/gpt-oss-20b",
  "messages": [
    {
      "role": "user",
      "content": "Explain quantum computing in simple terms"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 4096,
  "stream": true,
  "top_p": 1
}'

Technical Specifications

Model Architecture & Performance

Model Size 20.9B Params
Context Length 131.1k Tokens
Quantization fp16
Tokens/Second 386
Architecture Compact Mixture-of-Experts (MoE) with SwiGLU activations, Token-choice MoE, Alternating attention mechanism
Precision FP4 quantization (MXFP4), 8-bit precision support
License Apache 2.0
Release Date August 2024
Developers OpenAI

Pricing

Pay-per-use, no commitments

Input Tokens $0.05/1M Tokens
Output Tokens $0.28/1M Tokens

API Reference

Complete parameter documentation

Parameter Type Default Description
stream boolean true Enable streaming responses for real-time output.
temperature number 0.7 Controls randomness. Higher values mean more creative but less predictable output.
max_tokens number 4096 Maximum number of tokens to generate in the response.
top_p number 1 Nucleus sampling: considers tokens with top_p probability mass.

Explore the full request and response schema in our external API documentation

Performance

Strengths & considerations

Strengths Considerations
Compact Mixture-of-Experts (MoE) design with SwiGLU activations
Token-choice MoE optimized for single-GPU efficiency
Native FP4 quantization for optimal inference speed
Single B200 GPU deployment capability
131K context window with efficient memory usage
Adjustable reasoning effort levels for task-specific optimization
Supports function calling with defined schemas
Apache 2.0 license for commercial use
Smaller than largest frontier models
May require fine-tuning for specialized domains
MoE architecture complexity for some use cases

Use cases

Recommended applications for this model

Function calling with schemas
Web browsing and browser automation
Agentic tasks
Chain-of-thought reasoning
Local and low-latency deployments
Rapid prototyping and development support
Code generation and optimization
Customer support automation
Content generation and editing
Process automation and workflow optimization

Enterprise
Platform Integration

Docker

Docker Support

Official Docker images for containerized deployments

Kubernetes

Kubernetes Ready

Production-grade KBS manifests and Helm charts

SDK

SDK Libraries

Official SDKs for Python, Javascript, Go, and Java

Don't let your AI control you. Control your AI the Qubrid way!

Have questions? Want to Partner with us? Looking for larger deployments or custom fine-tuning? Let's collaborate on the right setup for your workloads.

"Qubrid AI reduced our document processing time by over 60% and significantly improved retrieval accuracy across our RAG workflows."

Enterprise AI Team

Document Intelligence Platform