What is GPT-OSS-120B good for?

Self-hosted or third-party-hosted text work under Apache 2.0. A mixture of experts activating 5.1B parameters per token, servable on a single high-memory GPU.

When is GPT-OSS-120B not a good fit?

Image input, since it is text only. Its knowledge is older than the rest of OpenAI's lineup, and memory follows the full 117B parameters, not the 5.1B active.

What is the cheapest way to run GPT-OSS-120B?

Hosted, unless you push serious volume. Geodd charges $0.04 in / $0.18 out per 1M tokens. The cheapest rental that fits is 8x RTX 3060 at $288 a month, which costs the same as about 5B tokens a month on that API.

Can I self-host GPT-OSS-120B?

Yes. The weights are Apache 2.0 licensed. At 4-bit it needs about 68 GB of GPU memory, which starts at roughly $288 a month on the cheapest rental that fits.

Open weights · Apache 2.0

GPT-OSS-120B

OpenAI's first open-weight model, released August 2025: a 117B-parameter MoE with 5.1B active that fits on a single 80 GB GPU, under Apache 2.0.

Jump to: Specs Pricing Self-hosting Similar models FAQ More from OpenAI

Visit website Compare vs other LLMs →

Cheapest via Geodd

Input: $0.04 / 1M tokens
Output: $0.18 / 1M tokens

9 providers

Key Specifications

Context window: 131K tokens
Max output: 131K tokens
Knowledge cutoff: Jun 2024
Released: Aug 2025
Parameters: 117B, 5.1B active
Inputs: Text

Capabilities Show details: Reasoning Thinks before it answers, always on or as a switchable mode. Function calling Connect to external tools, APIs, and systems. Structured output Return responses in structured formats like JSON.

Hosted API pricing

Input tokens M Output tokens M

Provider	Input / 1M tokens	Output / 1M tokens	Cost at 10M in + 2M out
Geodd Cheapest	$0.04	$0.18	$0.76	View
Novita	$0.05	$0.25	$1.00	View
DigitalOcean	$0.06	$0.39	$1.38	View
Hyperstack	$0.10	$0.40	$1.80	View
Lyceum	$0.15	$0.60	$2.70	View
Azure	$0.15	$0.60	$2.70	View
Together AI	$0.15	$0.60	$2.70	View
Replicate	$0.18	$0.72	$3.24	View
Cloudflare	$0.35	$0.75	$5.00	View

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Estimated cost to self-host

GPT-OSS-120B needs about 68 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 8× RTX 3060 at about $288 a month.

That costs the same as roughly 5B tokens a month on Geodd's API. Self-hosting is more expensive below that volume.

Precision	Cheapest, 32K context	Cheapest, full 131K context
4-bitINT4 / FP4	8× RTX 3060 68 GB VRAM · $288/mo	8× RTX 3060 71 GB VRAM · $288/mo
8-bitFP8 / INT8	8× RTX 3090 120 GB VRAM · $806/mo	8× RTX 3090 124 GB VRAM · $806/mo
16-bitFP16 / BF16	8× RTX A6000 237 GB VRAM · $3,168/mo	8× RTX A6000 241 GB VRAM · $3,168/mo

Estimates based on median on-demand rates for Nvidia GPUs. Memory is weights plus KV cache for one request, using FP8 KV cache where supported and FP16/BF16 otherwise. Break-even assumes a 5:1 input-to-output ratio. No guarantee of runtime support, usable performance, or that a matching quantized build exists. How we estimate costs.

Similarly priced models

The models nearest GPT-OSS-120B by blended rate, each at its own cheapest provider.

Model	Blended / 1M	Input / 1M	Output / 1M	Context	Cutoff	vs GPT-OSS-120B
Qwen3.7-Flash Alibaba Cloud	$0.0467	$0.03	$0.13	1M		−26%
GPT-OSS-20B OpenAI	$0.0483	$0.03	$0.14	131K	Jun 2024	−24%
Command R7B Cohere	$0.0583	$0.04	$0.15	128K		−8%
Gemma 3 12B Instruct Google Cloud	$0.0583	$0.05	$0.10	128K	Aug 2024	−8%
Llama 3.2 1B Meta	$0.0583	$0.03	$0.20	128K	Dec 2023	−8%
GPT-OSS-120B This model OpenAI	$0.0633	$0.04	$0.18	131K	Jun 2024
Nemotron 3 Nano 30B A3B Nvidia	$0.075	$0.05	$0.20	262K	Jun 2025	+18%
Llama 3 8B Meta	$0.0833	$0.05	$0.25	8K	Mar 2023	+32%
Qwen3-Coder-30B-A3B Alibaba Cloud	$0.0917	$0.06	$0.25	262K		+45%
Llama 3.2 3B Meta	$0.0983	$0.05	$0.34	128K	Dec 2023	+55%
Qwen3-30B-A3B FP8 Alibaba Cloud	$0.0983	$0.05	$0.34	33K		+55%

Prices are USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.

Runpod

Our sponsor

Spin Up a GPU in Seconds - No Setup Required

Deploy AI Models Globally in 30+ Regions

Scale from 0 to 1000 GPUs on Demand

PyTorch, Tensorflow & Docker Ready

Learn more

Frequently Asked Questions

What is GPT-OSS-120B good for?: Self-hosted or third-party-hosted text work under Apache 2.0. A mixture of experts activating 5.1B parameters per token, servable on a single high-memory GPU.
When is GPT-OSS-120B not a good fit?: Image input, since it is text only. Its knowledge is older than the rest of OpenAI's lineup, and memory follows the full 117B parameters, not the 5.1B active.
What is the cheapest way to run GPT-OSS-120B?: Hosted, unless you push serious volume. Geodd charges $0.04 in / $0.18 out per 1M tokens. The cheapest rental that fits is 8x RTX 3060 at $288 a month, which costs the same as about 5B tokens a month on that API.
Can I self-host GPT-OSS-120B?: Yes. The weights are Apache 2.0 licensed. At 4-bit it needs about 68 GB of GPU memory, which starts at roughly $288 a month on the cheapest rental that fits.

More from OpenAI

Model	Context	Cutoff	Input / 1M	Output / 1M
GPT-OSS-20B Open weights	131K	Jun 2024	$0.03	$0.14
GPT-5 Nano	400K	May 2024	$0.05	$0.40
GPT-4.1 Nano	1M	Jun 2024	$0.10	$0.40
GPT-4o Mini	128K	Oct 2023	$0.15	$0.60
GPT-5.6 Luna	1M	Feb 2026	$0.20	$1.20
GPT-5.4 Nano	400K	Aug 2025	$0.20	$1.25
GPT-5 Mini	400K	May 2024	$0.25	$2.00
GPT-4.1 Mini	1M	Jun 2024	$0.40	$1.60