GPT OSS 20B
Review GPT OSS 20B on key metrics including price, context length, throughput, and model features.
AuthorOpenAI
Context Length131.1k
Supports Tools
OpenAI’s 21B-parameter open-weight Mixture-of-Experts (MoE) model, released under the Apache 2.0 license. Features 3.6B active parameters per forward pass, optimized for low-latency inference and deployability on consumer or single-GPU hardware. Trained in OpenAI’s Harmony response format, it supports reasoning level configuration, fine-tuning, and agentic capabilities such as function calling and structured outputs.
Activity
Last 14 daysPrompt
161MCompletion
14MTotal
174MStartup
Startup
Latency (p50)0.11s
Throughput (p50)384.1 tok/s
Pricing
Input$0.02/M tokens
Output$0.10/M tokens
Features
Input Modalitiestext, file
Output Modalitiestext
Supported EndpointsChat Completions
Vision
Supports Tools