• gpt-oss-120b — for production, general purpose, high reasoning use cases that fits into a single H100 GPU (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)

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.
• Native MXFP4 quantization: The models are trained with native MXFP4 precision for the MoE layer, making gpt-oss-120b run on a single H100 GPU and the gpt-oss-20b model run within 16GB of memory.

• Original Model Card
• vLLM Documentation

Send Request

curl <AZUREML_ENDPOINT_URL> \
    -X POST \
    -d '{"model":"openai/gpt-oss-120b","input":"What is Deep Learning?"}' \
    -H "Authorization: Bearer <AZUREML_TOKEN>" \
    -H "Content-Type: application/json"

Supported Parameters

• model (string): Model ID used to generate the response, in this case since only a single model is deployed within the same endpoint you can either set it to openai/gpt-oss-120b or leave it blank instead.
• input (str or array): A text, image, or file inputs to the model, or even a list of messages comprising the conversation so far, used to generate the response. Depending on the model you use, different message types (modalities) are supported, like text, images, and audio; whilst in this case only text generation is supported so image and audio inputs are disallowed.

Example payload

{
  "model": "openai/gpt-oss-120b",
  "input": "What is Deep Learning?",
  "max_output_tokens": 1024,
  "temperature": 0.6,
  "reasoning": {
    "effort": "medium"
  }
}