OpenAI: Gpt Oss 20B
Released Recently|131K context|$0.04/M input tokens|$0.16/M output tokens
GPT-OSS-20B is an open-weight, 21B-parameter Mixture-of-Experts language model with 3.6B active parameters per forward pass. Optimized for lower-latency inference while maintaining high performance across reasoning, code generation, and general tasks. Features configurable reasoning levels and native tool use capabilities.
Speed
Intelligence
Price (1M Tokens)$0.04
Inputs
Text
Outputs
Text
Pricing
Input
$0.04
Cached input
N/A
Output
$0.16
gpt-oss-20b
$0.04
GPT-4o
$2.50
GPT-4.1
$2.00
Use Case
Fast Code Generation
Advanced AI capability for specialized tasks
Real-time Summarization
Advanced AI capability for specialized tasks
Classification Tasks
Advanced AI capability for specialized tasks
Quick Problem Solving
Advanced AI capability for specialized tasks
Cost-Effective AI Applications
Advanced AI capability for specialized tasks
Features
Configurable Reasoning
Adjustable reasoning depth for different tasks
Tool Use
Native function calling capabilities
Structured Output
Generate structured data formats
Open Source
Open-weight model with Apache 2.0 license
Low Latency
Optimized for fast inference
Cost Effective
Competitive pricing for high performance