gpt-oss-20b
Summarizationby OpenAI
gpt-oss-20b is OpenAI's open-weight reasoning model for solving problems, writing and debugging code, summarizing complex information, and answering questions from supplied context. Choose it for text tasks that require connecting information, following detailed instructions, and working through multiple steps.
Its efficient mixture-of-experts architecture activates 3.6 billion of its 21 billion parameters per token. On ZeroGPU, it runs on eligible edge GPUs with cloud fallback, bringing versatile reasoning and text generation to the distributed edge network.
Specifications
Parameters
21B (3.6B active)
Context length
131,072 tokens
Task
Summarization
Provider
OpenAI
Billing
Per token
API
OpenAI-compatible
Pricing
Input
$0.02
per 1M tokens
Output
$0.10
per 1M tokens