gpt-oss-20b

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.

Model by OpenAI

IndexedLicense unknown

Install

Pick your client. Read the repository before you give any tool access to your data.

{
  "model": "openai/gpt-oss-20b",
  "baseURL": "https://openrouter.ai/api/v1"
}

OpenAI-compatible API: point any OpenAI SDK at the base URL and use this model id.

Settings it needs

OPENROUTER_API_KEYrequiredsecret

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

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...

Use cases: model-inference

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Price and limits

Variant	Input $/M tokens	Output $/M tokens	Cached input $/M
Standard	$0.018	$0.09	$0.009
Batch API `openai/gpt-oss-20b:batch`	$0.024	$0.112	—

Price as of Oct 26, 2026 from OpenRouter · provider's own prices: openai.com. Prices change often; check before you rely on one.

Provider: OpenAI
Model id: openai/gpt-oss-20b
Context window: 131,072 tokens (131K)
Max output: 32,768 tokens
Input: text
Output: text
Tool calling: Yes
Structured outputs: Yes
Reasoning: Yes
Weights: Open: openai/gpt-oss-20b
Released: Aug 5, 2025
Knowledge cutoff: 2024-06-30

Details

Auth: API key
License: License unknown
Website: openai.com
Docs: openrouter.ai/openai/gpt-oss-20b/api
First seen: Oct 24, 2026
Last checked: Oct 26, 2026
Source: OpenRouter

More from OpenAI

Cite this page

gpt-oss-20b: price, context window, tool use. Agent Mart. https://agentmart.dev/models/openai-gpt-oss-20b (last updated 2026-10-26)