Magica logo

gpt-oss-120b Model Specs, Costs & Benchmarks (July 2026)

gpt-oss-120b, developed by OpenAI, features a context window of 131.1K tokens. The model costs $0.04 per million tokens for input and $0.17 per million tokens for output. It was released on August 5, 2025, and has achieved impressive scores in various benchmarks.
Access gpt-oss-120b & 210+ other AI models all in one platformTry Magica for free

Overview

gpt-oss-120bgpt-oss-120b
Model Provider
The organization behind this AI's development
OpenAI logoOpenAI
Input Context Window
Maximum input tokens this model can process at once
131.1K
tokens
Output Token Limit
Maximum output tokens this model can generate at once
131.1K
tokens
Release Date
When this model first became publicly available
August 5th, 2025
Knowledge Cutoff
Latest training-data date reported by the provider
June 30, 2024

Pricing

gpt-oss-120bgpt-oss-120b
Input Token Cost
Cost per million input tokens
$0.04
per million tokens
Output Token Cost
Cost per million output tokens
$0.17
per million tokens

Capabilities & Features

gpt-oss-120bgpt-oss-120b
Input Types
Supported input formats
text
Output Types
Supported output formats
text
Tokenizer
Text encoding system
GPT
Key Features
Advanced capabilities
βœ“ Function Callingβœ“ Structured Outputβœ“ Reasoning Mode
Reasoning Controls
Defaults and configurable reasoning effort
Always enabledEffort: High, Medium, LowDefault: Medium
Open Source
Model availability

Benchmarks

gpt-oss-120bgpt-oss-120b
Intelligence Index
Overall model quality across independent evaluations
23.8
(Artificial Analysis index; higher is better)
Coding Index
Programming performance across independent evaluations
30.4
(Artificial Analysis index; higher is better)
Agentic Index
Ability to complete multi-step agentic tasks
13.2
(Artificial Analysis index; higher is better)
Best Design Arena Score
Highest human-preference Elo score across design arenas
1,052 Elo
(#90 in Game Dev (40.6% win rate))

Compare This Model

See how gpt-oss-120b compares with other top models

Compare gpt-oss-120b with top models in each category: