The publication AI reads — a remote MCP server, nothing to install.Connect your agent →

openai/gpt-oss-20b

openai/gpt-oss-20b is a openai record on this register. The Hugging Face model API lists the pipeline tag as text-generation. The safetensors index gives an exact parameter count of 20,914,757,184. Architectural context length (max_position_embeddings) is 131,072. The listed licence is apache-2.0. The Hub repository was created on 4 Aug 2025, which is the release date this register uses.

Primary source: the Hugging Face model card for openai/gpt-oss-20b. Fields below come from that card, the Hub model API, and the repository’s own config.json when those files exist. A field we cannot source is omitted rather than guessed.

Organisationopenai
ReleasedRepo creation date on Hugging Face4 Aug 2025
Last modified26 Aug 2025
ParametersExact, from the safetensors index20.9B 20,914,757,184
Context lengthmax_position_embeddings — architectural maximum, not necessarily served128K 131,072
Licenceapache-2.0
Pipeline / taskpipeline_tag on the Hugging Face model APItext-generation
File formatssafetensors
Librarylibrary_name on the Hugging Face model APItransformers
Architecturegpt_oss
Layers24
Vocabulary201,088
DownloadsAt last check5.9m
Likes5.2k
GatedNo

How to run

Safetensors weights are on the Hugging Face repository. The parameter count on this page came from that index.

The Hugging Face model API lists the library as transformers.

Load it from huggingface.co/openai/gpt-oss-20b. This page does not add install steps that the Hub files do not state.

Agent capabilities

Derived from the model’s own chat template, with the match counts behind each finding.

  • ●Tool calling27 matches in template
  • ●Reasoning / thinking12 matches in template
  • ●System prompt1 match in template
  • ○Image inputno evidence in template
  • ○Video inputno evidence in template
  • ○Audio inputno evidence in template

Questions this record can answer

When was gpt-oss-20b released?
The Hugging Face repository was created on 4 Aug 2025, which is the date this register uses.
How many parameters does gpt-oss-20b have?
The safetensors index gives 20,914,757,184 parameters, shown here as 20.9B. That figure is exact, not rounded.
What is the context length of gpt-oss-20b?
131,072 tokens. That is max_position_embeddings from the model's own config.json — the architectural maximum, not necessarily the context a provider serves.
What licence is gpt-oss-20b under?
The Hub card lists apache-2.0.
Is gpt-oss-20b gated?
No. The Hugging Face model API does not mark this repository as gated.
Does the gpt-oss-20b chat template show tool calling?
The chat template contains evidence of tool calling.

Where each field came from

  • Hugging Face model API — releasedAt, lastModified, downloads, likes, task, license, gated, parameters, libraryName, formats. Checked 18 Oct 2026.
  • config.json — contextLength, layers, vocabSize, architecture. Checked 18 Oct 2026.
  • chat template — capabilities. Checked 18 Oct 2026.

First recorded 24 Sept 2026, last checked 18 Oct 2026. This record is compiled automatically from the sources above. Where a field is blank, we could not source it and have not guessed. Canonical repository: huggingface.co/openai/gpt-oss-20b.