GPT Oss 120b
by OpenAI
Instruct
Reasoning
Tools
GPT Oss 120b is a large-scale 120 billion parameter Mixture-of-Experts (MoE) language model from OpenAI, designed to excel in advanced reasoning, chain-of-thought workflows, and agentic applications. Optimized for high reasoning efficiency, it allows configurable effort levels to balance speed and accuracy depending on task requirements. Released as an open-weight model under the permissive Apache 2.0 license, gpt-oss-120b enables full customization and commercial use, making it highly versatile for developers building intelligent systems, research applications, or specialized AI agents.
Provider | Context Size | Throughput | Latency | Input Cost | Output Cost |
|---|---|---|---|---|---|
Usage
Generate your API key and query the model through the OpenAI-compatible interface. The preference parameter allows you to define the routing strategy. For more details, see the documentation.
>Enter ↵