Back to models

GPT-5 nano

Fastest, most cost-efficient version of GPT-5

Context window128,000 tokens
Max output tokens128,000 tokens

Pricing

TypeInputOutput
Standard$0.05 / 1M tokens$0.40 / 1M tokens
Cached input$0.01 / 1M tokens

Parameters

ParameterDefaultRange
Max stop sequences0

Supported features

Capabilities

  • Streaming
  • Reasoning
  • System Prompt

Endpoints

  • Chat Completions
  • Batch

Use cases

  • text-chat

Model specifications

Model IDgpt-5-nano
FamilyOther
Access typeClosed
Input modalitiestext
Output modalitiestext
Last updatedJanuary 3, 2026
GPT-5 nano | ModelHub | ModelHub