GPT OSS 20B
Wandb textwandb/openai/gpt-oss-20b
Input
$0.0300
per 1M input tokens
Output
$0.1300
per 1M output tokens
Cache read
n/a
per 1M cached read tokens
Cache write
n/a
per 1M cache write tokens
Context window
131,000
Max output
131,072
Effective date
Sep 18, 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 18, 2026 | $0.03 | $0.13 | $0.06 |
| Aug 28, 2026 | $0.03 | $0.13 | $0.06 |
| Jun 15, 2026 | $5,000.00 | $20,000.00 | $8,750.00 |
GPT OSS 20B on other providers
Darkbloom
· $0.0145 in / $0.0700 out
Openrouter
· $0.0180 in / $0.0900 out
Deepinfra
· $0.0300 in / $0.1400 out
Inferenceapis
· $0.0400 in / $0.1900 out
Inferenceapis
· $0.0400 in / $0.1900 out
Gmi
· $0.0400 in / $0.1500 out
Ovhcloud
· $0.0400 in / $0.1500 out
Novita
· $0.0400 in / $0.1500 out
Together Ai
· $0.0500 in / $0.2000 out
Fireworks Ai
· $0.0700 in / $0.3000 out
Fireworks Ai
· $0.0700 in / $0.3000 out
Tensormesh
· $0.0700 in / $0.2800 out
Other Wandb models
wandb/openai/gpt-oss-120b
· $0.1700/Mtok out
wandb/ibm-granite/granite-4.1-8b
· $0.1000/Mtok out
wandb/JetBrains/Mellum2-12B-A2.5B-Instruct
· $0.1000/Mtok out
wandb/OpenPipe/Qwen3-14B-Instruct
· $0.2200/Mtok out
wandb/ibm-granite/granite-4.2-8b
· $0.1500/Mtok out
wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B
· $0.2000/Mtok out
Source: litellm. Confirm against the provider's official pricing before relying on these figures.