gpt-oss-20b
Rank #62
openai
openai/gpt-oss-20b
Usage data date 2026-07-27 · updated daily
Usage and specs
Daily rank#62
Daily tokens98.2B
Daily requests24M
Daily change
−30.0%
Context window131.1K
Released
What is gpt-oss-20b
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 lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.
gpt-oss-20b capabilities
Input: Text Output: Text
gpt-oss-20b API pricing
Input · per 1M tokens$0.03
Output · per 1M tokens$0.14
USD list-price snapshot, not independently verified; confirm current pricing and terms on the provider site before purchase.