GPT OSS 120B
Review GPT OSS 120B on key metrics including price, context length, throughput, and model features.
AuthorOpenAI
Context Length131.1k
Supports Tools
An open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI, designed for high-reasoning, agentic, and general-purpose production use cases. Activates 5.1B parameters per forward pass and is optimized for single H100 GPU deployment with native MXFP4 quantization. Supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.
Activity
Last 14 daysPrompt
40MCompletion
13MTotal
53MStartup
Startup
Latency (p50)0.36s
Throughput (p50)348.6 tok/s
Pricing
Input$0.07/M tokens
Output$0.30/M tokens
Features
Input Modalitiestext, file
Output Modalitiestext
Supported EndpointsChat Completions
Vision
Supports Tools