gpt-oss-20b (batch)
by OpenAI
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per f
Models
gpt-oss-20b (batch)
Added 3 Sept 2026
Overview
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
How to use / API access
Call via OpenRouter with model id `openai/gpt-oss-20b:batch`.
- openrouter ·
openai/gpt-oss-20b:batchDocs
OpenRouter id: openai/gpt-oss-20b:batch
Benchmarks
- Coding Index (artificial-analysis) : 20.7 index
- Agentic Index (artificial-analysis) : 1.4 index
- Design Arena dataviz (other) : 951 elo · #108
- Design Arena website (other) : 865 elo · #124
Notes
gpt-oss-20b (batch) is listed in the EDNA Models directory from the OpenRouter catalogue.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.