OpenAI: gpt-oss-20b

openai/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...

Modalities

In / out price

$0.018 / $0.090 per 1M

Context

131K

Released

Aug 5, 2025

Why use gpt-oss-20b

Step-by-step reasoning mode
Tool and function calling (agent-ready)
Structured (JSON) outputs

Pricing

Input	$0.018 / 1M tokens
Output	$0.090 / 1M tokens
Cached input (read)	$0.009 / 1M tokens

List prices via OpenRouter, checked daily. Real cost depends on the provider and on reasoning tokens.

How it ranks

Intelligence index9

Coding index20.7

Agentic index1.2

Source: Artificial Analysis (artificialanalysis.ai) via OpenRouter (openrouter.ai/rankings).

Cost calculator

Pick a task, set how often you run it, and compare what it costs on each model.

TaskInput tokens≈ 602 wordsOutput tokens≈ 1,504 wordsRuns per month

Input served from cache: 0%Repeated prompts (same instructions or document) are billed at the cheaper cache-read price where the model supports it.

Model	Per run	Per month	Per 1,000 runs
OpenAI: gpt-oss-20b	$0.0002	$0.194	$0.194

Estimates from list prices via OpenRouter; real bills vary by provider and reasoning tokens.

Will it fit? Context window simulator

Each square is about one page (500 words). Colored squares are your content; grey squares are free space in the model's context window.

Your content

Novel (90,000 words)

Total: about 120,000 tokens (≈ 90,226 words). Token counts are estimates.

Models

Zoom (square size): 6pxZoom out to see a whole million-token window at once.