OpenAI gpt-oss 120B: price on every cloud
Open weights · 117 billion parameters · Mixture of experts · 131,072-token context · licence apache-2.0
Per token, by cloud
| Cloud | Input, per 1M tokens | Output, per 1M tokens | Cheapest region |
|---|---|---|---|
| AWS | $0.075 | $0.30 | eu-north-1 · 15 regions |
| Google Cloud | $0.09 | $0.36 | global |
| Core42 | $0.15 | $0.37 | uae |
| Azure | $0.15 | $0.60 | australiaeast · 41 regions |
| OCI | $0.15 | $0.60 | global · 3 regions |
| Alibaba Cloud | — | — | not sold per token |
Run it yourself
It needs 73 GB of GPU memory at int4, the precision it ships in.
| Cloud | Cheapest instance that fits | GPUs | An hour | A month, around the clock |
|---|---|---|---|---|
| Azure | Standard_NC24ads_A100_v4 | 1 × A100 80 GB | $3.67 | $2,681 |
| Google Cloud | g4-standard-48 | 1 × RTX PRO 6000 96 GB | $4.50 | $3,285 |
| AWS | p5.4xlarge | 1 × H100 80 GB | $6.88 | $5,022 |
| Alibaba Cloud | ecs.gn8v.4xlarge | 1 × GPU H 96 GB | $7.31 | $5,337 |
At the cheapest per-token price, running it on Azure Standard_NC24ads_A100_v4 pays off above roughly 20.4 billion tokens a month.
More from OpenAI
Similar size, open weights
- Llama 3.3 70B
- Llama 4 Scout 17B
- Llama 3.1 70B
- NVIDIA-Nemotron-3-Super-120B-A12B-BF16
- Qwen3.5-122B-A10B-NVFP4
- Qwen3-Coder-Next-FP8 (Qwen)
Inside the UAE: sold in-country by Core42, Azure.
List prices collected 5 October 2026, refreshed every three hours. No negotiated rates or taxes.