# gpt-oss-120b

> OpenAI's open-weight 117B MoE reasoning model under Apache 2.0

- Maker: OpenAI
- Line: gpt-oss (Open Weight)
- Canonical page: https://ai-tldr.dev/models/gpt-oss-120b/
- Updated: 2026-06-18

## In short

gpt-oss-120b is OpenAI's larger open-weight language model, released August 5, 2025 alongside the smaller gpt-oss-20b. It has a 131K-token context window and costs $0.039 per million input tokens and $0.18 per million output tokens. You can use it through OpenRouter, Hugging Face and Fireworks AI.

## Facts

| Fact | Value | Source |
| --- | --- | --- |
| Context window | 131K (max output 131K) | [1] |
| Input price | $0.039 / 1M tokens | [2] |
| Output price | $0.18 / 1M tokens | [2] |
| Licence | Apache 2.0 · open weights | [1] |
| Released | 5 August 2025 | [3] |
| Parameters | 116.8B total / 5.1B active (MoE) | [1] |
| Knowledge cutoff | June 2024 | [1] |

## Sources

1. [openai/gpt-oss-120b — Hugging Face model card](https://huggingface.co/openai/gpt-oss-120b)
2. [gpt-oss-120b — OpenRouter pricing & benchmarks](https://openrouter.ai/openai/gpt-oss-120b)
3. [Introducing gpt-oss — OpenAI announcement](https://openai.com/index/introducing-gpt-oss/)

## Overview

gpt-oss-120b is OpenAI's larger open-weight language model, released August 5, 2025 alongside the smaller gpt-oss-20b. It is a 116.8B-parameter Mixture-of-Experts transformer that activates only about 5.1B parameters per token, and it ships under the permissive Apache 2.0 license — the first open-weight models OpenAI had released since GPT-2. The weights are freely downloadable from Hugging Face and the openai/gpt-oss GitHub repository.

Built for high-end reasoning and agentic work, gpt-oss-120b exposes a configurable reasoning effort (low / medium / high) with full chain-of-thought visibility, and natively supports function calling, web browsing, Python tool use, and structured outputs. OpenAI positions it as reaching near-parity with its proprietary o4-mini model on core reasoning benchmarks while running on a single 80GB GPU thanks to native MXFP4 quantization of the expert weights.

Because gpt-oss-120b is open-weight rather than served first-party by OpenAI, it is hosted across many inference providers (OpenRouter, Fireworks, Together, DeepInfra, Novita, Groq, AWS Bedrock, Databricks, and others), each setting its own price. It is text-only, trained primarily on English STEM, coding, and general-knowledge data, with a June 2024 knowledge cutoff and a 131,072-token context window.

## Benchmarks

- MMLU: 90% ([source](https://arxiv.org/html/2508.10925v1))
- GPQA Diamond (no tools): 80.1% ([source](https://arxiv.org/html/2508.10925v1))
- AIME 2024 (with tools): 96.6% ([source](https://arxiv.org/html/2508.10925v1))
- AIME 2025 (with tools): 97.9% ([source](https://arxiv.org/html/2508.10925v1))
- SWE-bench Verified: 62.4% ([source](https://arxiv.org/html/2508.10925v1))
- HealthBench: 57.6% ([source](https://arxiv.org/html/2508.10925v1))
- Humanity's Last Exam (with tools): 19% ([source](https://arxiv.org/html/2508.10925v1))
- Tau-Bench Retail: 67.8% ([source](https://arxiv.org/html/2508.10925v1))
- Artificial Analysis Intelligence Index (high): 24% ([source](https://artificialanalysis.ai/models/gpt-oss-120b))

## Pricing

- Input: $0.039 / 1M tokens per 1M tokens
- Output: $0.18 / 1M tokens per 1M tokens

gpt-oss-120b is open-weight, so it is not served first-party by OpenAI — prices vary by host. Figures shown are a representative low rate from OpenRouter providers (e.g. DeepInfra); other providers charge more. Self-hosting incurs only your own compute cost.

Source: https://openrouter.ai/openai/gpt-oss-120b

## Strengths

- State-of-the-art open-weight reasoning — near-parity with OpenAI o4-mini on core benchmarks
- Efficient MoE design: ~5.1B active params runs on a single 80GB GPU via native MXFP4 quantization
- Permissive Apache 2.0 license allowing commercial use and fine-tuning
- Configurable reasoning effort (low/medium/high) with full chain-of-thought access
- Strong agentic tooling: function calling, web browsing, Python execution, structured outputs
- 131K-token context window for long documents and agent traces
- Self-hostable open weights — no vendor lock-in, deployable on-prem

## Best for

- On-premise / private reasoning assistants where data cannot leave the org
- Agentic workflows requiring tool calling, browsing, and code execution
- Cost-controlled high-volume inference via self-hosting or cheap third-party providers
- Math, science, and competition-coding tasks (strong AIME and Codeforces results)
- Fine-tuning a frontier-class open model for domain-specific applications
- Research into chain-of-thought reasoning with fully visible reasoning traces

## How to access

- [OpenRouter](https://openrouter.ai/openai/gpt-oss-120b) — model id `openai/gpt-oss-120b`
- [Hugging Face](https://huggingface.co/openai/gpt-oss-120b) — model id `openai/gpt-oss-120b`
- [Fireworks AI](https://fireworks.ai/models/fireworks/gpt-oss-120b) — model id `accounts/fireworks/models/gpt-oss-120b`
- [NVIDIA NIM](https://build.nvidia.com/openai/gpt-oss-120b/modelcard) — model id `openai/gpt-oss-120b`
- [AWS Bedrock](https://ai-sdk.dev/playground/bedrock:openai.gpt-oss-120b) — model id `openai.gpt-oss-120b`

## gpt-oss (Open Weight) versions

- gpt-oss-120b (5 August 2025) — this page
- [gpt-oss-20b](https://ai-tldr.dev/models/gpt-oss-20b/) (5 August 2025)

## FAQ

### Is gpt-oss-120b free and open source?

The weights are released under the permissive Apache 2.0 license, so you can download, run, fine-tune, and deploy gpt-oss-120b commercially without copyleft restrictions. Running it still costs compute — either your own hardware or a paid inference provider — but there are no license fees.

### What hardware do I need to run gpt-oss-120b?

Thanks to native MXFP4 quantization of its Mixture-of-Experts weights, gpt-oss-120b fits on a single 80GB GPU such as an NVIDIA H100 or AMD MI300X. It has 116.8B total parameters but activates only about 5.1B per token.

### How does gpt-oss-120b compare to OpenAI's o4-mini?

OpenAI reports gpt-oss-120b reaches near-parity with the proprietary o4-mini on core reasoning benchmarks, and it matches or exceeds o4-mini on competition math (AIME), health questions (HealthBench), and tool calling, while being fully open-weight and self-hostable.

### Is gpt-oss-120b multimodal?

No. gpt-oss-120b is text-only — it does not accept image, audio, or video input. It supports a 131,072-token context window, configurable reasoning effort, and native tool use including function calling, browsing, and Python execution.

## Links

- [Introducing gpt-oss — OpenAI announcement](https://openai.com/index/introducing-gpt-oss/)
- [openai/gpt-oss-120b — Hugging Face model card](https://huggingface.co/openai/gpt-oss-120b)
- [gpt-oss-120b & gpt-oss-20b Model Card (arXiv 2508.10925)](https://arxiv.org/abs/2508.10925)
- [gpt-oss-120b — OpenAI API docs](https://developers.openai.com/api/docs/models/gpt-oss-120b)
- [openai/gpt-oss — official GitHub repository](https://github.com/openai/gpt-oss)
- [gpt-oss playground (gpt-oss.com)](https://gpt-oss.com/)
- [gpt-oss-120b — OpenRouter pricing & benchmarks](https://openrouter.ai/openai/gpt-oss-120b)
- [gpt-oss-120b — Artificial Analysis](https://artificialanalysis.ai/models/gpt-oss-120b)
- [gpt-oss-120b benchmarks](https://arxiv.org/html/2508.10925v1)

Source: AI/TLDR LLM registry, https://ai-tldr.dev/models/gpt-oss-120b/