gpt-oss API pricing
Every gpt-oss model we track, with the cheapest price per 1M tokens across 21 providers. Collected daily.
gpt-oss API prices by model
Standard (real-time) rates per 1M tokens, newest first. “Cheapest” is the lowest input price across every provider we track; batch and cached-input rates are on each model page.
| Model | Cheapest input | Output | Cheapest on |
|---|---|---|---|
| GPT-OSS-120B128K context | $0.037 | $0.170 | Deep Infra |
| GPT-OSS-20B128K context | $0.018 | $0.090 | OpenRouter |
gpt-oss price history
Average input price per 1M tokens across the providers serving each model, last 90 days.
Frequently Asked Questions
What is the cheapest gpt-oss API?
Of the 2 gpt-oss models we track, GPT-OSS-20B has the lowest input price right now: $0.018 per 1M input tokens on OpenRouter. Prices are collected daily from 21 providers — see the table above for every model.
Where is GPT-OSS-120B cheapest?
GPT-OSS-120B is served by 20 providers we track. The lowest standard input price is $0.037 per 1M tokens on Deep Infra. Throughput, latency and context limits differ between hosts, so check the model page before committing.