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.
Try NowLower-latency inference tasks
Consumer hardware deployment
Cost-efficient general-purpose tasks
131,072 tokens
131,072 tokens
$0.03
$0.14
$15
$0.19