whichllm — Browse and compare AI model specs and pricing

DInference

GPT OSS 120B model ID, context window & pricing

models.dev synced record

Quick facts

Model ID gpt-oss-120b
Source DInference
Context Window 131072
Pricing $0.07 input / $0.27 output per 1M tokens
Capabilities tool calling, temperature control, open weights

Model overview

GPT OSS 120B is an AI model from DInference with 131072 token context window and text input support.

Published pricing is $0.07 input and $0.27 output per 1M tokens.

  • Workloads that use text inputs with text outputs.
  • Agent and tool workflows that need function calling.
Model ID gpt-oss-120b
Provider DInference
Family -
Status -
Knowledge Cutoff -
Release Date 2025-08
Input Modalities text
Output Modalities text
Context Window 131072
Input Limit -
Output Limit 32768
Tool Calling Yes
Reasoning No
Structured Output -
Temperature Control Yes
Open Weights Yes
Input Cost / 1M tokens $0.07
Output Cost / 1M tokens $0.27
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens -
Cache Write Cost / 1M tokens -