OpenAI: gpt-oss-120b (exacto)

Text input Text output
Author's Description

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 to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

Key Specifications
Cost
$$
Context
131K
Parameters
120B
Released
Aug 05, 2025
Supported Parameters

This model supports the following parameters:

Frequency Penalty Max Tokens Stop Reasoning Tools Include Reasoning Top P Structured Outputs Tool Choice Presence Penalty Seed Response Format Temperature
Features

This model supports the following features:

Structured Outputs Reasoning Tools Response Format
Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.05
Completion $0.25

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Novita
Novita | openai/gpt-oss-120b:exacto 131K $0.05 / 1M tokens $0.25 / 1M tokens
DeepInfra
DeepInfra | openai/gpt-oss-120b:exacto 131K $0.05 / 1M tokens $0.24 / 1M tokens
Groq
Groq | openai/gpt-oss-120b:exacto 131K $0.15 / 1M tokens $0.6 / 1M tokens
Other Models by openai