OpenAI

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...

Context Window
131K tokens
Parameters
21B
Input Price
$0.03/1M
Output Price
$0.13/1M
Price Tier
budget
Provider
OpenAI

How to Use OpenAI: gpt-oss-20b

With CoreAI, you can start chatting with OpenAI: gpt-oss-20b instantly — no separate subscription needed. CoreAI lets you chat with OpenAI: gpt-oss-20b alongside 300+ other AI models from OpenAI and other providers like OpenAI, Anthropic, Google, Meta, and more.

  1. Download the CoreAI app for iOS, Android, or use the Web App
  2. Select OpenAI: gpt-oss-20b from the model selector
  3. Start chatting, comparing, or creating with AI

OpenAI: gpt-oss-20b at a Glance

OpenAI: gpt-oss-20b holds the #273 spot for context size out of 392 chat models in the CoreAI catalog — 131K tokens, roughly 98,304 words or 197 pages of text in a single conversation. On price, it is the #8 cheapest of 128 budget-tier models by input cost. It joined the catalog on 2025-08-05. It supports step-by-step reasoning (thinking mode).

OpenAI: gpt-oss-20b Compared to Its Closest Alternatives

SpecOpenAI: gpt-oss-20bOpenAI: gpt-oss-120bGoogle: Gemma 4 26B A4B (free)inclusionAI: Ling-2.6-flash
ProviderOpenAIOpenAIGoogleInclusionai
Input $/1M tokens$0.03$0.03Free$0.01
Output $/1M tokens$0.13$0.17Free$0.03
Context window131K131K131K262K
Reasoning modeYesYesYesNo
Image inputNoNoYesNo
Price tierbudgetbudgetbudgetbudget

Every model in this table is available on CoreAI — open the web app and run the same prompt through OpenAI: gpt-oss-20b and OpenAI: gpt-oss-120b side by side to judge with your own eyes.

What OpenAI: gpt-oss-20b Actually Costs in Practice

A typical question (about 1,000 tokens in, 500 out) runs $0.00010 on OpenAI: gpt-oss-20b's raw per-token rates; a heavy session with a 50K-token document costs about $0.002. On CoreAI you don't juggle these numbers — one subscription covers OpenAI: gpt-oss-20b and 300+ other models under a plan usage limit, with no API keys. See plans.

More OpenAI Models

OpenAI

OpenAI: GPT-5.6 Luna Pro

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://ask-coreai.com), served with `reasoning.mode` set to `pro` for higher-quality
1050K budget
OpenAI

OpenAI: GPT-5.6 Luna Pro (batch)

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://ask-coreai.com), served with `reasoning.mode` set to `pro` for higher-quality
1050K budget
OpenAI

OpenAI: GPT-5.6 Luna

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classific
1050K budget
OpenAI

OpenAI: GPT-5.6 Luna (batch)

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classific
1050K budget
OpenAI

OpenAI: GPT-5.6 Terra Pro

GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://ask-coreai.com), served with `reasoning.mode` set to `pro` for higher-qualit
1050K standard
OpenAI

OpenAI: GPT-5.6 Terra Pro (batch)

GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://ask-coreai.com), served with `reasoning.mode` set to `pro` for higher-qualit
1050K standard

Frequently Asked Questions about OpenAI: gpt-oss-20b

What is OpenAI: gpt-oss-20b's context window?

OpenAI: gpt-oss-20b handles 131K tokens of context — roughly 98,304 words, or about 197 pages of text in one conversation.

How much does OpenAI: gpt-oss-20b cost?

OpenAI: gpt-oss-20b's underlying rates are $0.03 per 1M input tokens and $0.13 per 1M output tokens. On CoreAI it is included in one subscription alongside 300+ models, so there is no per-token billing to manage.

Can OpenAI: gpt-oss-20b process images?

No — OpenAI: gpt-oss-20b is text-only. If you need image understanding, its budget-tier peers with vision are listed in the comparison table above.

Does OpenAI: gpt-oss-20b support reasoning or thinking mode?

Yes. OpenAI: gpt-oss-20b can work through problems step by step before answering; on CoreAI you can toggle thinking mode per message.

How can I use OpenAI: gpt-oss-20b without an API key?

Open the CoreAI web app or the iOS/Android app, pick OpenAI: gpt-oss-20b in the model selector, and chat — no API key, no per-token billing. One subscription covers OpenAI: gpt-oss-20b and 300+ other models.

What are the best alternatives to OpenAI: gpt-oss-20b?

The closest alternatives on CoreAI are OpenAI: gpt-oss-120b, Google: Gemma 4 26B A4B (free), inclusionAI: Ling-2.6-flash — similar tier and capability. The fastest way to choose is running one prompt through them side by side in CoreAI's Compare view.

Read More about OpenAI: gpt-oss-20b

Try OpenAI: gpt-oss-20b Now

Chat with OpenAI: gpt-oss-20b and 300+ other AI models — all in one app.

Use Web App Download App →