Back to all models

GPT-5 Nano

Ultra-efficient GPT-5 variant for high-volume applications with reasoning support.

gpt-5-nano
STABLEGet StartedView uptime
400,000 context
Starting at $0.05/M (10% off) input tokens
Starting at $0.36/M (10% off) output tokens
Streaming
Tools
Reasoning
JSON Output

Select Provider

All Providers for GPT-5 Nano

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

OpenAI
Context: 400k10% off
Input
$0.05$0.045
/M tokens
Cached
$0.005$0.0045
/M tokens
Output
$0.4$0.36
/M tokens
+ $0.010 per search
Get Started
Azure
Context: 400k
Input
$0.05
/M tokens
Cached
$0.005
/M tokens
Output
$0.4
/M tokens
Get Started