gpt oss 120b
openai/gpt-oss-120bChat- Function calling
- Reasoning
OpenAI, released Aug 2025, updated Aug 2025
gpt oss 120b (openai/gpt-oss-120b) is a 116.8B-parameter chat model from OpenAI with a 131,072-token context window and 117,964 max output tokens, priced at $0.09/1M input and $0.42/1M output tokens. Available via the haimaker.ai OpenAI-compatible API.
API usage
from openai import OpenAI
client = OpenAI(
base_url="https://api.haimaker.ai/v1",
api_key="YOUR_API_KEY",
)
response = client.chat.completions.create(
model="openai/gpt-oss-120b",
messages=[
{"role": "user", "content": "Hello, how are you?"}
],
)
print(response.choices[0].message.content)Replace YOUR_API_KEY with a key from your haimaker account. Get an API key or read the developer docs.
Benchmarks
gpt oss 120b scores 50 of 100 on the haimaker intelligence index, 42nd of 53 open-weight models, from 21 benchmarks.
| Benchmark | Source | Score |
|---|---|---|
| Aider Polyglot | Independent | 41.8% |
| LiveCodeBench | Other vendor | 89.9% |
| SWE-bench Pro | Other vendor | 16.2% |
| SWE-rebench | Independent | 24.6% |
| Terminal-Bench 2.x | Independent | 18.7% |
| Benchmark | Source | Score |
|---|---|---|
| Arena-Hard v2 | Other vendor | 79.6% |
| IFBench | Other vendor | 70.8% |
| IFEval | Other vendor | 93.2% |
| LMArena Text | Independent | 1351.8 Elo |
| Benchmark | Source | Score |
|---|---|---|
| AIME 2025-2026 | Other vendor | 91.7% |
| Epoch Capabilities Index | Independent | 140.2 |
| GPQA Diamond | Independent | 75.8% |
| Humanity's Last Exam | Other vendor | 18.4% |
| MMLU | Other vendor | 88.6% |
| MMLU-Pro | Other vendor | 80.8% |
| Benchmark | Source | Score |
|---|---|---|
| INCLUDE | Other vendor | 74% |
| MMLU-ProX | Other vendor | 74.5% |
| MMMLU | Other vendor | 78.2% |
| SEA-HELM | Independent | 66.1% |
| Benchmark | Source | Score |
|---|---|---|
| AA-LCR | Other vendor | 50.7% |
| LongBench v2 | Other vendor | 48.2% |
Sources use different harnesses and settings, so treat these as a starting point. Compare intelligence and price across models
Overview
GPT Oss 120B is a chat model by OpenAI. It has 116.8B parameters. It supports a 131K token context window. Supports function calling, reasoning.
Specifications
| Mode | Chat |
|---|---|
| Supports | Function calling, Reasoning |
| Not supported | Vision, Web search, URL context |
| Licence | Apache 2.0 |
| Architecture | GptOssForCausalLM |
| Model type | gpt_oss |
| Library | transformers |
Frequently asked questions
What is the context window of gpt oss 120b?
gpt oss 120b (openai/gpt-oss-120b) has a 131,072-token context window and supports up to 117,964 output tokens per request.
How much does gpt oss 120b cost?
gpt oss 120b is priced at $0.09 per 1M input tokens and $0.42 per 1M output tokens when accessed via the haimaker.ai OpenAI-compatible API.
What features does gpt oss 120b support?
gpt oss 120b supports function calling, reasoning.
How do I use gpt oss 120b via API?
Send requests to https://api.haimaker.ai/v1/chat/completions with model "openai/gpt-oss-120b" using any OpenAI-compatible SDK. Authentication uses a Bearer API key from https://app.haimaker.ai.
Model card
Written by the model’s publisher on Hugging Face. Shown without its logos and badges.
Try gpt-oss · Guides · Model card · OpenAI blog
Welcome to the gpt-oss series, OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
We’re releasing two flavors of these open models:
gpt-oss-120b— for production, general purpose, high reasoning use cases that fit into a single 80GB GPU (like NVIDIA H100 or AMD MI300X) (117B parameters with 5.1B active parameters)gpt-oss-20b— for lower latency, and local or specialized use cases (21B parameters with 3.6B active parameters)
Both models were trained on our harmony response format and should only be used with the harmony format as it will not work correctly otherwise.
Note
This model card is dedicated to the larger
gpt-oss-120bmodel. Check outgpt-oss-20bfor the smaller model.
Highlights
- Permissive Apache 2.0 license: Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment.
- Configurable reasoning effort: Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.
- Full chain-of-thought: Gain complete access to the model’s reasoning process, facilitating easier debugging and increased trust in outputs. It’s not intended to be shown to end users.
- Fine-tunable: Fully customize models to your specific use case through parameter fine-tuning.
- Agentic capabilities: Use the models’ native capabilities for function calling, web browsing, Python code execution, and Structured Outputs.
- MXFP4 quantization: The models were post-trained with MXFP4 quantization of the MoE weights, making
gpt-oss-120brun on a single 80GB GPU (like NVIDIA H100 or AMD MI300X) and thegpt-oss-20bmodel run within 16GB of memory. All evals were performed with the same MXFP4 quantization.
Inference examples
Transformers
You can use gpt-oss-120b and gpt-oss-20b with Transformers. If you use the Transformers chat template, it will automatically apply the harmony response format. If you use model.generate directly, you need to apply the harmony format manually using the chat template or use our openai-harmony package.
To get started, install the necessary dependencies to setup your environment:
pip install -U transformers kernels torch
Once, setup you can proceed to run the model by running the snippet below:
from transformers import pipeline
import torch
model_id = "openai/gpt-oss-120b"
pipe = pipeline(
"text-generation",
model=model_id,
torch_dtype="auto",
device_map="auto",
)
messages = [
{"role": "user", "content": "Explain quantum mechanics clearly and concisely."},
]
outputs = pipe(
messages,
max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])
Alternatively, you can run the model via Transformers Serve to spin up a OpenAI-compatible webserver:
transformers serve
transformers chat localhost:8000 --model-name-or-path openai/gpt-oss-120b
Learn more about how to use gpt-oss with Transformers.
vLLM
vLLM recommends using uv for Python dependency management. You can use vLLM to spin up an OpenAI-compatible webserver. The following command will automatically download the model and start the server.
uv pip install --pre vllm==0.10.1+gptoss \
--extra-index-url https://wheels.vllm.ai/gpt-oss/ \
--extra-index-url https://download.pytorch.org/whl/nightly/cu128 \
--index-strategy unsafe-best-match
vllm serve openai/gpt-oss-120b
Learn more about how to use gpt-oss with vLLM.
PyTorch / Triton
To learn about how to use this model with PyTorch and Triton, check out our reference implementations in the gpt-oss repository.
Ollama
If you are trying to run gpt-oss on consumer hardware, you can use Ollama by running the following commands after installing Ollama.
# gpt-oss-120b
ollama pull gpt-oss:120b
ollama run gpt-oss:120b
Learn more about how to use gpt-oss with Ollama.
LM Studio
If you are using LM Studio you can use the following commands to download.
# gpt-oss-120b
lms get openai/gpt-oss-120b
Check out our awesome list for a broader collection of gpt-oss resources and inference partners.
Download the model
You can download the model weights from the Hugging Face Hub directly from Hugging Face CLI:
# gpt-oss-120b
huggingface-cli download openai/gpt-oss-120b --include "original/*" --local-dir gpt-oss-120b/
pip install gpt-oss
python -m gpt_oss.chat model/
Reasoning levels
You can adjust the reasoning level that suits your task across three levels:
- Low: Fast responses for general dialogue.
- Medium: Balanced speed and detail.
- High: Deep and detailed analysis.
The reasoning level can be set in the system prompts, e.g., "Reasoning: high".
Tool use
The gpt-oss models are excellent for:
- Web browsing (using built-in browsing tools)
- Function calling with defined schemas
- Agentic operations like browser tasks
Fine-tuning
Both gpt-oss models can be fine-tuned for a variety of specialized use cases.
This larger model gpt-oss-120b can be fine-tuned on a single H100 node, whereas the smaller gpt-oss-20b can even be fine-tuned on consumer hardware.
Citation
@misc{openai2025gptoss120bgptoss20bmodel,
title={gpt-oss-120b & gpt-oss-20b Model Card},
author={OpenAI},
year={2025},
eprint={2508.10925},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2508.10925},
}Related chat models
Run gpt oss 120b through one API
OpenAI-compatible. Switch models by changing one string.