← model directory
openai
OpenAI: gpt-oss-120b
openai/gpt-oss-120b
↓ runs free on your own hardware⚙ tool calling
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
specs & pricing
- Type
- text
- Provider
- openai
- Model ID
- openai/gpt-oss-120b
- Capabilities
- tools, reasoning
- Context window
- 131K tokens
- Self-hostable
- Yes — runs on your own GPU
- Input price
- $0.041 / 1M tokens
- Output price
- $0.19 / 1M tokens
Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.