OpenAI gpt-oss 20B: price on every cloud
Open weights · 21 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 | $0.035 | $0.15 | eu-north-1 · 15 regions |
| Google Cloud | $0.07 | $0.25 | global |
| Azure | $0.07 | $0.30 | australiaeast · 36 regions |
| OCI | $0.07 | $0.30 | global · 3 regions |
| Core42 | $0.10 | $0.30 | uae |
| Alibaba Cloud | — | — | not sold per token |
Run it yourself
It needs 13.1 GB of GPU memory at int4, the precision it ships in.
| Cloud | Cheapest instance that fits | GPUs | An hour | A month, around the clock |
|---|---|---|---|---|
| AWS | g4dn.xlarge | 1 × T4 16 GB | $0.526 | $384 |
| Azure | Standard_NC4as_T4_v3 | 1 × T4 16 GB | $0.526 | $384 |
| Google Cloud | g2-standard-4 | 1 × L4 24 GB | $0.7068 | $516 |
| Alibaba Cloud | ecs.gn6i-c4g1.xlarge | 1 × T4 16 GB | $1.12 | $816 |
At the cheapest per-token price, running it on AWS g4dn.xlarge pays off above roughly 6.0 billion tokens a month.
More from OpenAI
Similar size, open weights
Inside the UAE: sold in-country by Azure, Core42.
List prices collected 5 October 2026, refreshed every three hours. No negotiated rates or taxes.