Microsoft: Phi 4 Mini

Microsoft: Phi 4 Mini

byMicrosoft

Phi 4 Mini is a language model from Microsoft released on Dec 11, 2024. It reads text and writes text, with a 8K token context window and up to 4K tokens per reply.

Show more

It costs $0.075 per million input tokens and $0.30 per million output tokens.

It supports tool calling, and its weights are open, so you can host it yourself.

3 providers serve it, including Azure, Azure Cognitive Services and NanoGPT.

Modalities
In / out price
$0.075 / $0.30 per 1M
Context
8K
Max output
4K
Released
Dec 11, 2024
Knowledge cutoff
Jun 2024
  • Tool calling
  • Structured output
  • Reasoning
  • Prompt caching
  • Open weights
  • Free to use

Phi 4 Mini pricing

USD, as listed on Nov 22, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.

Input$0.075 / 1M tokens
Output$0.30 / 1M tokens

Phi 4 Mini providers

3 providers serve it, including Azure, Azure Cognitive Services and NanoGPT. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.

ProviderInput /MOutput /MCache read /MContextMax output
Azure$0.075$0.30n/a128K4K
Azure Cognitive Services$0.075$0.30n/a128K4K
NanoGPT$0.17$0.68$0.0858K4K

What Phi 4 Mini costs per month

Pick a workload close to yours or type your own volumes.

Phi 4 Mini per month
$8.78
Without caching
$8.78
Per request
$0.0003

Supported request parameters

What you can set when you call Phi 4 Mini through an OpenAI compatible API.

  • Toolstools
  • Temperaturetemperature

Alternatives to Phi 4 Mini

Models that take the same inputs and call tools, closest in price, cheaper ones first.

  • Reads text. Tool calling, structured output, reasoning. Served by 41 providers.

    by openaiAug 5, 2025128K context$0.07/M input tokens$0.30/M output tokens41 providers

  • Reads text, images and files. Tool calling, structured output. Served by 9 providers.

    by mistralaiDec 2, 2025131K context$0.10/M input tokens$0.10/M output tokens9 providers

  • Reads text and images. Tool calling, structured output, reasoning.

    by thinkingmachinesNov 21, 2026$0.075/M input tokens$0.30/M output tokens

  • Reads text and images. Tool calling, reasoning.

    by z-aiDec 8, 2025$0.04/M input tokens$0.40/M output tokens

  • Reads text. Tool calling, structured output, reasoning. Served by 15 providers.

    by qwenApr 28, 2025$0.08/M input tokens$0.28/M output tokens15 providers

  • Reads text and images. Tool calling, structured output, reasoning. Served by 2 providers.

    by bytedanceJul 26, 2025$0.07/M input tokens$0.30/M output tokens2 providers

More from Microsoft

All Microsoft models

Phi 4 Mini questions

How much does the Phi 4 Mini API cost?

$0.075 per million input tokens and $0.30 per million output tokens. The estimator on this page turns that into a monthly bill for your own workload.

What is the context window of Phi 4 Mini?

8,192 tokens of input, and it can write up to 4,096 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.

Which providers serve Phi 4 Mini?

3 providers serve it, including Azure, Azure Cognitive Services and NanoGPT. Prices differ by host, so the Providers table on this page lists each one with its input and output price.

Does Phi 4 Mini support tool calling?

Yes. It accepts tool definitions, which is what an agent needs to call your APIs.

Is Phi 4 Mini open source?

Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.

When was Phi 4 Mini released?

Dec 11, 2024, with training data up to Jun 2024.

Catalog data from models.dev (MIT licensed), refreshed daily, last on Nov 22, 2026. The summary is written from these facts.