gpt-oss-120b
Text Generationby OpenAI
gpt-oss-120b is OpenAI’s open-weight reasoning model built for advanced text generation, coding, research, and agentic workflows. It supports function calling, structured outputs, streaming, and multilingual use, making it a strong fit for applications that need deeper reasoning and reliable multi-step execution. On ZeroGPU, gpt-oss-120b runs across the hybrid inference cloud, using optimized cloud and edge capacity to deliver strong performance while balancing speed and cost for production workloads.
Specifications
Parameters
120B
Context length
131,072 tokens
Task
Text Generation
Provider
OpenAI
Billing
Per token
API
OpenAI-compatible
Pricing
Input
$0.15
per 1M tokens
Output
$0.60
per 1M tokens