Skip to main content

GPT-5.4 nano

OpenAI's cheapest, fastest GPT-5-class model for high-volume tasks.

GPT-5.4 nano specifications

ProviderOpenAI
Context window400,000 tokens (400K)
Input price$0.20 / 1M tokens
Output price$1.25 / 1M tokens
InputsText, Images
Reasoning modeYes
Vision (image input)Yes
Tool / function callingYes
Native real-time webNo
Open-weightNo
ReleasedApril 2026

Pricing & context web-verified June 2026 confirm on OpenAI's pricing page.

What GPT-5.4 nano is best for

  • High-volume classification and extraction
  • Cheap, fast chat
  • Cost-sensitive pipelines

How to prompt GPT-5.4 nano

  • Use it for well-scoped, repetitive tasks where a frontier model is overkill.
  • Give tight, explicit output formats — small models follow structure better than freeform asks.
  • Batch similar requests to keep cost low.

Work with GPT-5.4 nano

Frequently asked questions

What is GPT-5.4 nano's context window?

GPT-5.4 nano has a 400,000-token context window (about 400K tokens) — the maximum amount of text it can consider at once.

How much does GPT-5.4 nano cost?

Via the OpenAI API, GPT-5.4 nano costs $0.20 per 1M input tokens and $1.25 per 1M output tokens (web-verified June 2026). Output tokens cost more, so the length of the model's reply usually drives the bill.

Is GPT-5.4 nano multimodal?

Yes — GPT-5.4 nano accepts Text, Images as input, not just text.

Is GPT-5.4 nano open-weight?

No — GPT-5.4 nano is available only through the OpenAI API, not as downloadable weights.