gpt oss 120b
Input per million tokens
$0.0294
Unchanged since November 4, 2026
- November 4, 2026: $0.0294
Output per million tokens
$0.147
Unchanged since November 4, 2026
- November 4, 2026: $0.147
01Model page
gpt oss 120b
In early accessgpt-oss-120b
Alias gpt-oss-120b > gpt-oss-120b-b5c939de
Hugging Faceopenai/gpt-oss-120b
GptOssForCausalLM / 117B parameters
We are inviting early-access interest while we develop the platform.
02The model's fields
Licensing or usage conditionsapache-2.0
03Versions and aliases
| Model version | Status | Released | Retires | Hugging Face revision |
|---|---|---|---|---|
| gpt-oss-120b-b5c939deCURRENT | Live | b5c939de8f75 |
- gpt-oss-120bpoints atgpt-oss-120b-b5c939de
04Rates, per pool
Rates
Approved-provider pool
Per million tokens
On demand
- Input
- $0.0294
- Cached input
- $0.00294
- Output
- $0.147
Batch
Batch is not offered for this model.
| Input | Cached input | Output | |
|---|---|---|---|
| On demand | $0.0294 | $0.00294 | $0.147 |
| Batch | Batch is not offered for this model. | ||
Personal GPUs
Per million tokens
On demand
- Input
- $0.0294
- Cached input
- Billed as input at launch
- Output
- $0.147
Batch
Batch is not offered for this model.
| Input | Cached input | Output | |
|---|---|---|---|
| On demand | $0.0294 | Billed as input at launch | $0.147 |
| Batch | Batch is not offered for this model. | ||
On personal GPUs, every input token is billed at the input rate.