/Models/gpt-oss-120b
OpenAI

gpt-oss-120b

Lowest Price
$0.04
per 1M tokens
Providers
2
Available
Context
N/A
tokens

Price Comparison

ProviderInput / OutputLatencyStatus
OpenRouterOpenRouterLowest
$0.04/$0.19
...
Verified
DeepInfraDeepInfra
$0.04/$0.19
...
Verified

About This Model

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. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function ca...

Quick Start