GPT-OSS-120B API pricing on Prime Intellect
Every Prime Intellect GPT-OSS-120B rate we track, compared against 20 providers serving the same model.
The cheapest GPT-OSS-120B input price we currently track is $0.030/1M on OpenRouter.
Prime Intellect GPT-OSS-120B rates
Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.
| Mode | Input | Output |
|---|---|---|
| Standard | $0.350/1M | $0.750/1M |
About GPT-OSS-120B
- Creator
- OpenAI
- Context
- 128K
- Modalities
- text
- Knowledge cutoff
- Jan 2025
- Tool calling
- Yes
- Open weights
- Yes
GPT-OSS-120B on other providers
- OpenRouter$0.030/1M
- Deep Infra$0.037/1M
- Geodd$0.039/1M
- Crusoe$0.050/1M
- GMI Cloud$0.050/1M
- Novita AI$0.050/1M
- Amazon AWS$0.070/1M
- OVHcloud$0.090/1M
- Baseten$0.100/1M
- DigitalOcean$0.100/1M
- Hyperstack$0.100/1M
- Groq$0.150/1M
- OpenRelay$0.150/1M
- Together AI$0.150/1M
- Scaleway$0.168/1M
- IO.NET$0.168/1M
- SambaNova$0.220/1M
- Cerebras$0.350/1M
- Heabsy$0.700/1M
About Prime Intellect
Prime Intellect is an AI research company and compute platform. It aggregates on-demand GPUs and reserved clusters from many providers behind one account, and runs Prime Intellect Inference, an OpenAI-compatible API that serves open-weight models directly and routes to proprietary models, plus hosted reinforcement-learning training through its Lab platform.
Frequently Asked Questions
How much does GPT-OSS-120B cost on Prime Intellect?
Prime Intellect serves GPT-OSS-120B from $0.350 per 1M input tokens, across 1 tracked pricing mode. Prices are collected daily — see the table above for current input, output, and cached-input rates.
Is Prime Intellect the cheapest way to run GPT-OSS-120B?
Prime Intellect ranks #18 of 20 providers we track serving GPT-OSS-120B. The cheapest input price right now is on OpenRouter. Price is only one factor — throughput, latency, and context limits differ between providers.
Does Prime Intellect offer batch or cached pricing for GPT-OSS-120B?
We track 1 GPT-OSS-120B offering from Prime Intellect. Batch and cached-input rates appear in the table above when the provider publishes them; blank cells mean we have no current figure for that mode.