How much does the gpt-oss-120b API cost?

gpt-oss-120b costs $0.1 per million input tokens and $0.5 per million output tokens. A workload of 10M input and 1.5M output tokens per month costs about $1.75.

What is the context window of gpt-oss-120b?

gpt-oss-120b supports a context window of 131,072 tokens (131K), with up to 131K output tokens per response.

Is gpt-oss-120b open source?

Yes — gpt-oss-120b is an open-weights model released under the Apache 2.0 license, so it can be downloaded and self-hosted.

What are the best alternatives to gpt-oss-120b?

The closest alternatives by overall capability are Qwen3-Max, Gemini 3 Pro, Gemini 2.5 Pro, DeepSeek V3.2. See the comparison pages for detailed head-to-head breakdowns.

gpt-oss-120b

Name: gpt-oss-120b
Price: 0.1 USD
Author: OpenAI

OpenAI·Aug 2025reasoningopen weights · Apache 2.0

gpt-oss-120b was OpenAI's first open-weights language model since GPT-2: a 117B-parameter mixture-of-experts with only 5.1B active parameters per token, released under Apache 2.0. It delivers reasoning quality near o4-mini, runs on a single 80GB GPU, and supports adjustable reasoning effort. Hosted inference is extremely cheap across providers, and self-hosting is realistic for mid-size teams — a rare combination of pedigree, license freedom and efficiency.

Benchmark results

Where it shines

Permissive Apache 2.0 license with OpenAI pedigree
Runs on a single 80GB GPU (or hosted for ~$0.10/M input)
Adjustable reasoning effort like the proprietary o-series

Alternatives to gpt-oss-120b

Qwen3-Max

Alibaba's trillion-parameter API flagship — frontier-adjacent quality with strong agentic tool use at mid-tier prices.

Gemini 3 Pro

Google's November 2025 frontier breakout — 91.9% GPQA Diamond and 37.5% HLE made it the reasoning leader of its generation.

Gemini 2.5 Pro

Google's 2025 workhorse flagship — first mainstream thinking model with a 1M context, still widely deployed.

DeepSeek V3.2

The sparse-attention release that halved DeepSeek's already-lowest-in-class prices while keeping GPT-class quality.

Frequently asked questions

How much does the gpt-oss-120b API cost?: gpt-oss-120b costs $0.1 per million input tokens and $0.5 per million output tokens. A workload of 10M input and 1.5M output tokens per month costs about $1.75.
What is the context window of gpt-oss-120b?: gpt-oss-120b supports a context window of 131,072 tokens (131K), with up to 131K output tokens per response.
Is gpt-oss-120b open source?: Yes — gpt-oss-120b is an open-weights model released under the Apache 2.0 license, so it can be downloaded and self-hosted.
What are the best alternatives to gpt-oss-120b?: The closest alternatives by overall capability are Qwen3-Max, Gemini 3 Pro, Gemini 2.5 Pro, DeepSeek V3.2. See the comparison pages for detailed head-to-head breakdowns.