Home / Models / OpenAI / GPT-4.1 Mini

GPT-4.1 Mini pricing and routing profile

GPT-4.1 Mini from OpenAI lists at $0.40 per million input tokens and $1.60 per million output tokens, with a 1,047,576-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$0.40
Output, per 1M tokens$1.60
Cached input, per 1M$0.10
Context window1.05M
Confidence signalNot exposed

Tool callingStructured output

Cost per 1,000 requests

Request shapeList cost
Classification or routing (600 tokens in, 10 out)$0.256
Chat reply (2,000 in, 400 out)$1.44
Retrieval-augmented answer (8,000 in, 500 out)$4.00

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-4.1 Mini. It can still be the model Gimbix falls back to when a cheaper model is unsure.

Who serves GPT-4.1 Mini

HostInput / output per 1MLog probabilitiesUptime, last 30 min
Azure$0.40 / $1.60no100.0%
OpenAI$0.40 / $1.60no99.8%
Azure$0.44 / $1.76no100.0%

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-4.1 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
Qwen3.7 Plus$0.32 / $1.2820%
Qwen3.5 Plus 2026-02-15$0.26 / $1.5621%
Muse Glimmer 30B$0.30 / $1.2025%
MiniMax M3$0.30 / $1.2025%
MiniMax M2.7$0.30 / $1.2025%
MiniMax M2$0.30 / $1.2025%

Questions

How much does GPT-4.1 Mini cost?

GPT-4.1 Mini lists at $0.40 per million input tokens and $1.60 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 $1.44 per 1,000 requests.

What is the context window of GPT-4.1 Mini?

1,047,576 tokens.

Can a cheaper model replace GPT-4.1 Mini?

Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match GPT-4.1 Mini on one half of your requests and make at most three answers worse on the other.