GPT OSS 120B
Baseten textbaseten/openai/gpt-oss-120b
Input
$0.1000
per 1M input tokens
Output
$0.5000
per 1M output tokens
Cache read
$0.1000
per 1M cached read tokens
Cache write
n/a
per 1M cache write tokens
Context window
128,072
Max output
128,072
Effective date
Sep 23, 2026
Estimate a workload
Enter token counts to see the cost at this model's rates.
Estimated cost:
$0.00
Price history
blended $ per 1M tokens (3:1)| Effective | Input | Output | Blended |
|---|---|---|---|
| Sep 23, 2026 | $0.10 | $0.50 | $0.20 |
| Jun 15, 2026 | $0.10 | $0.50 | $0.20 |
GPT OSS 120B on other providers
Wandb
· $0.0300 in / $0.1700 out
Deepinfra
· $0.0370 in / $0.1700 out
Openrouter
· $0.0370 in / $0.1700 out
Kyma
· $0.0473 in / $0.2303 out
Gmi
· $0.0500 in / $0.2500 out
Novita
· $0.0500 in / $0.2500 out
Sail
· $0.0600 in / $0.4000 out
Ovhcloud
· $0.0800 in / $0.4000 out
Fireworks Ai
· $0.1500 in / $0.6000 out
Fireworks Ai
· $0.1500 in / $0.6000 out
Groq
· $0.1500 in / $0.6000 out
Scaleway
· $0.1500 in / $0.6000 out
Other Baseten models
baseten/decision-models/baseten-joey-2b-latest
· $0.0000/Mtok out
baseten/decision-models/baseten-elephant-9b-latest
· $0.0000/Mtok out
baseten/decision-models/baseten-mammoth-27b-latest
· $0.0000/Mtok out
baseten/deepseek-ai/DeepSeek-V4-Flash-0731
· $0.2600/Mtok out
baseten/zai-org/GLM-5.3-Flash
· $0.5000/Mtok out
baseten/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B
· $0.5000/Mtok out
Source: litellm. Confirm against the provider's official pricing before relying on these figures.