Deploy GPT-OSS
Text & ChatGPT-OSS is OpenAI’s open-weight model family, available here in 20B and 120B configurations. It supports reasoning and tool-use applications; integration and hardware requirements depend on the variant.
Set up a GPT-OSS workspace
Starting at $0.66/hr on dedicated GPU
Model configurations (2)
| Model | GPU | VRAM | Price | Action |
|---|---|---|---|---|
GPT-OSS 20B Medium (20B) | L4 | 24 GB | $0.66/hr | Deploy |
GPT-OSS 120B Large (120B) | A100 80GB PCIe | 80 GB | $1.85/hr | Deploy |
Prices include the service fee. Charges follow actual running time.
Requirements
The listed configuration specifies 24–80GB cloud GPUs across the listed variants. Actual local VRAM requirements vary with model variant, precision, quantization, resolution, and workflow settings.
On ModelPilot, deploy on a dedicated cloud GPU (up to 80GB VRAM) starting at $0.66/hr. Review the template’s required setup steps and settings before launch.
Use Cases
- Function calling and tool use
- Chain-of-thought reasoning
- AI agent development
- Enterprise deployments
Related Models
Frequently Asked Questions
How much GPU memory is allocated for GPT-OSS?
The listed ModelPilot variants use 24–80GB cloud GPUs. Local memory needs vary with the variant, precision, quantization, and workflow settings.
How much does it cost to run GPT-OSS?
Starting at $0.66/hr on a dedicated GPU. Charges are calculated from actual running time, with auto-stop when credits run out.
How long does GPT-OSS take to deploy?
Startup time depends on model downloads, container setup, cached files and GPU availability. Review the estimate for your selected template; it is not a guaranteed time to a finished result. Dedicated GPU time is billed while allocated, including startup.
Can I run GPT-OSS on my local GPU?
It depends on the selected variant, precision, quantization, and workflow settings. Compare the variants below with your available VRAM; the table shows ModelPilot's cloud GPU allocation, not a universal local minimum.
Ready to deploy GPT-OSS?
Choose a GPU, review the estimated rate, and check the template’s setup requirements before launching.