Parameters
117B MoEOpen Model Catalogue
OpenAI
Text generationReasoning
gpt-oss 120B
openai/gpt-oss-120bOpenAI flagship — runs on a single 80 GB GPU
Min VRAM
≈ 66 GBHardware
1 × 80 GB GPUOpenAI-compatible API with a per-workload key — drop-in for existing SDKs.
Dedicated GPUs — your model, your instance, no shared queues.
Billed by the second with auto-shutdown — never pay for idle time you didn't plan.