Home / Models / OpenAI / GPT-5.4 Nano

GPT-5.4 Nano pricing and routing profile

GPT-5.4 Nano from OpenAI lists at $0.20 per million input tokens and $1.25 per million output tokens, with a 400,000-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$0.20
Output, per 1M tokens$1.25
Cached input, per 1M$0.02
Context window400K
Confidence signalNot exposed

Tool callingStructured outputReasoning control

Cost per 1,000 requests

Request shapeList cost
Classification or routing (600 tokens in, 10 out)$0.133
Chat reply (2,000 in, 400 out)$0.90
Retrieval-augmented answer (8,000 in, 500 out)$2.23

Before prompt caching. Try your own shape in the cost calculator.

Can Gimbix route to it first?

Not as a first-answer model through OpenRouter: no host returns token log probabilities for GPT-5.4 Nano. It can still be the model Gimbix falls back to when a cheaper model is unsure.

Who serves GPT-5.4 Nano

HostInput / output per 1MLog probabilitiesUptime, last 30 min
OpenAI$0.10 / $0.625no100.0%
Azure$0.20 / $1.25no100.0%
OpenAI$0.20 / $1.25no100.0%
Azure$0.22 / $1.38no—

A host that lists log probabilities may still omit them; Gimbix checks each one before relying on it.

Cheaper models that can answer first

Models priced below GPT-5.4 Nano that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.

ModelInput / output per 1MCheaper on a chat reply
Qwen3.6 Flash$0.188 / $1.138%
Qwen3 Coder Flash$0.195 / $0.97513%
Qwen3 Next 80B A3B Thinking$0.15 / $1.2013%
Qwen3.6 35B A3B$0.15 / $1.0022%
Qwen3 Next 80B A3B Instruct$0.10 / $1.1029%
Llama 4 Maverick$0.188 / $0.65229%

Questions

How much does GPT-5.4 Nano cost?

GPT-5.4 Nano lists at $0.20 per million input tokens and $1.25 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $0.90 per 1,000 requests.

What is the context window of GPT-5.4 Nano?

400,000 tokens.

Can a cheaper model replace GPT-5.4 Nano?

Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match GPT-5.4 Nano on one half of your requests and make at most three answers worse on the other.