GPT-OSS 20B is the smaller of OpenAI's two open-weight reasoning models: 21B parameters with 3.6B active, text input only. it is the low-cost sibling of GPT-OSS 120B and is the GPT-OSS model on the free plan.
pick it if
you want low-cost text work at under a tenth of GPT-OSS 120B input
you want Apache 2.0 weights that run within 16GB of memory
you want adjustable reasoning effort: low, medium or high
skip it if
you need image input; it reads text only
prompts repeat heavily: no cached-input discount applies here
Qwen3.7 Flash was the lowest-cost tier of Alibaba's Qwen3.7 line, below Qwen3.7 Plus and Max: a vision-language model taking text, image and video input. Alibaba positioned it as an upgrade on Qwen3.6 Flash for multimodal and agent work.
pick it if
you wanted the cheapest Qwen3.7 tier for high-volume work
you needed a 1M-token window with image and video input
your prompts repeated, since cache hits billed at a fraction of input
skip it if
you need a live model; it was retired on 2026-09-17
you need audio input; it took text, image and video only
faq
which is cheaper, GPT-OSS 20B or Qwen3.7 Flash?
GPT-OSS 20B lists the lower output price; input prices match. on a coding-agent session (2M tokens in, 60,000 out) GPT-OSS 20B costs $0.07 and Qwen3.7 Flash $0.07.