gpt-oss-20b

OpenAI

gpt-oss-20b is a 21-billion parameter open-weight model released by OpenAI under the Apache 2.0 license. Its core feature is a Mixture-of-Experts (MoE) architecture that uses only 3.6B active parameters, enabling low-latency inference and deployment on consumer GPUs. The model also supports fine-tuning, function calling, tool use, and structured outputs.

API Pricing

Input$0.11 / 1M tokens
Output$0.55 / 1M tokens

Specifications

Context128K tokens
Modalitiestext
Featuresthinking, function calling, structured outputs

Frequently asked questions

What is gpt-oss-20b?

gpt-oss-20b is a 21-billion parameter open-weight model released by OpenAI under the Apache 2.0 license. Its core feature is a Mixture-of-Experts (MoE) architecture that uses only 3.6B active parameters, enabling low-latency inference and deployment on consumer GPUs. The model also supports fine-tuning, function calling, tool use, and structured outputs.

What is the context length of gpt-oss-20b?

gpt-oss-20b has a 128,000 token context window.

How much does gpt-oss-20b cost?

On AIHubMix, gpt-oss-20b costs $0.11 per million input tokens and $0.55 per million output tokens.

What modalities does gpt-oss-20b support?

gpt-oss-20b accepts text input.

What capabilities does gpt-oss-20b support?

gpt-oss-20b supports thinking, function calling and structured outputs. Per-protocol parameter support is listed in the capability table on this page.

How do I call gpt-oss-20b via API?

gpt-oss-20b is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to gpt-oss-20b — no other code changes needed.

Who created gpt-oss-20b?

gpt-oss-20b is developed by OpenAI. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

When was gpt-oss-20b released?

gpt-oss-20b was released on August 5, 2025 by OpenAI.

Free version: GPT Oss 20B (free)

More models from OpenAI

See all OpenAI models →

GPT 6.1 Sol

by OpenAI

GPT-6.1 Sol is OpenAI's latest model in the GPT-6 series, specifically designed for…

$2/1M in · $10/1M out
1,050,000 tokens context

GPT 6 Luna

by OpenAI

GPT-6 Luna is OpenAI's latest and most efficient model, designed for focused…

$0.1/1M in · $0.5/1M out
1,050,000 tokens context

GPT 6 Sol

by OpenAI

GPT-6 Sol is OpenAI's latest model in the GPT-6 series, specifically designed for complex…

$2/1M in · $10/1M out
1,050,000 tokens context

GPT 6 Astra

by OpenAI

GPT-6 Astra is OpenAI's newest and most intelligent model, with industry-leading…

$10/1M in · $50/1M out
1,050,000 tokens context

GPT Live Transcribe

by OpenAI

OpenAI's latest realtime speech-to-text model, built for low-latency use — it streams…

GPT Realtime 2.1

by OpenAI

GPT-Realtime-2.1 is a reasoning speech-to-speech model for the Realtime API, with tool…

$4/1M in · $24/1M out
128,000 tokens context

Use gpt-oss-20b via the AIHubMix unified API — one interface for every major LLM.