Home / Models / OpenAI / GPT-5.4 Mini

GPT-5.4 Mini pricing and routing profile

GPT-5.4 Mini from OpenAI lists at $0.75 per million input tokens and $4.50 per million output tokens, with a 400,000-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$0.75
Output, per 1M tokens$4.50
Cached input, per 1M$0.075
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)$0.495
Chat reply (2,000 in, 400 out)$3.30
Retrieval-augmented answer (8,000 in, 500 out)$8.25

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 Mini. It can still be the model Gimbix falls back to when a cheaper model is unsure.

Who serves GPT-5.4 Mini

HostInput / output per 1MLog probabilitiesUptime, last 30 min
OpenAI$0.375 / $2.25no—
Azure$0.75 / $4.50no100.0%
OpenAI$0.75 / $4.50no100.0%
Azure$0.825 / $4.95no—
OpenAI$1.50 / $9.00no—

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 Mini 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
Kimi K2.6$0.65 / $3.4119%
Kimi K2.7 Code$0.656 / $3.3020%
Qwen3 Coder Plus$0.65 / $3.2521%
Qwen3.5 397B A17B$0.55 / $3.5024%
Qwen3 VL 235B A22B Thinking$0.40 / $4.0027%
Kimi K2 Thinking$0.60 / $2.5033%

Questions

How much does GPT-5.4 Mini cost?

GPT-5.4 Mini lists at $0.75 per million input tokens and $4.50 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 $3.30 per 1,000 requests.

What is the context window of GPT-5.4 Mini?

400,000 tokens.

Can a cheaper model replace GPT-5.4 Mini?

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