GPT OSS Ultra 120B
GPT OSS Ultra 120B is OpenAI's language model. An ultra-fast open-weight 120B LLM variant in the GPT OSS series, optimized for high-speed inference at large scale.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Cheapest Instances to Run It
Cloud GPU instances that can host GPT OSS Ultra 120B, ranked by cheapest on-demand price. The model needs about 288 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| g7e.24xlarge |  AWS | 4× RTX PRO Server 6000 | 384 GB | $16.57/hr | us-east-1 | |
| g4-standard-192 |  GCP | 4× nvidia-rtx-pro-6000 | 384 GB | $18.00/hr | us-central1 | |
| p4d.24xlarge | AWS | 8× A100 | 320 GB | $21.96/hr | us-west-2 | |
Other Models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| GPT-5.6 Sol | — | 1.1M | $2.50 | $15.00 | |
| GPT-5.6 Terra | — | 1.1M | $1.00 | $6.00 | |
| GPT-5.6 Luna | — | 1.1M | $0.100 | $0.600 | |
| GPT-5.5 | — | 1.1M | $2.50 | $15.00 | |
| GPT-5.4 Mini | Mini | 400K | $0.375 | $2.25 | |
| GPT-5.4 Nano | Nano | 400K | $0.100 | $0.625 | |
| GPT-5.4 | — | 1.1M | $1.25 | $7.50 | |
| GPT-5.3 Codex | — | 400K | $1.75 | $14.00 | |
| GPT-5.2 Codex | — | 400K | $1.75 | $14.00 | |
| GPT-5.2 | — | 410K | $0.875 | $7.00 |