Microsoft
Reasoning

Phi-4 Mini

Tiny

Compact Phi-4, 4B parameters tuned for cheap reasoning on commodity hardware.

Phi-4 Mini is a reasoning AI model from Microsoft. It costs $0.0400 per million input tokens and $0.1600 per million output tokens (blended $0.0760/M), with a 128,000-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.0400/M
per million input tokens
OUTPUT
$0.1600/M
per million output tokens
BLENDED 70/30
$0.0760/M
unchanged since 3 May
CONTEXT
128,000
tokens

Hand-maintained from Microsoft's published pricing; no check date on record.

What it is good at
  • Edge / consumer-GPU friendly
  • Open weights (MIT)
  • Strong math for 4B
Typical use cases
  • On-device reasoning
  • Cheap STEM tutoring

Benchmarks

vs. best public score
MMLU67.3%
Multitask academic knowledge across 57 subjects. Source: Microsoft (self-reported), MMLU, read 2026-11-10.
Graduate-level science questions, "Google-proof". No source recorded yet.
MATH64%
High-school competition math problems. Source: Microsoft (self-reported), MATH, read 2026-11-10.
HumanEval74.4%
Python function synthesis from docstrings. Source: Microsoft (self-reported), HumanEval, read 2026-11-10.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

More from Microsoft

See all 8 →

Frequently asked questions

How much does Phi-4 Mini cost?

Phi-4 Mini costs $0.0400 per million input tokens and $0.1600 per million output tokens, for a blended reference rate of $0.0760 per million tokens.

What is Phi-4 Mini's context window?

Phi-4 Mini supports up to 128,000 tokens of context in a single request.

What is Phi-4 Mini best for?

Phi-4 Mini is well suited to Edge / consumer-GPU friendly, Open weights (MIT) and Strong math for 4B.

Who makes Phi-4 Mini?

Phi-4 Mini is developed and served by Microsoft. It was released in Feb 2025.

Terms used on this page