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 $0.040 per million input tokens and $0.160 per million output tokens (blended $0.076/M), with a 128,000-token context window.
INPUT
$0.040/M
per million input tokens
OUTPUT
$0.160/M
per million output tokens
CONTEXT
128,000
tokens
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
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 →Phi-4
Frontier SLM · 16,000 ctx
in $0.070/Mout $0.280/M
Phi-3.5 Mini
Compact · 128,000 ctx
in $0.130/Mout $0.520/M
Phi-3.5 MoE
MoE · 128,000 ctx
in $0.160/Mout $0.640/M
Phi-3 Medium
Balanced · 128,000 ctx
in $0.170/Mout $0.680/M
Phi-3 Mini
Tiny · 128,000 ctx
in $0.130/Mout $0.520/M
Phi-3 Small
Compact · 128,000 ctx
in $0.150/Mout $0.600/M
Frequently asked questions
How much does Phi-4 Mini cost?
Phi-4 Mini costs $0.040 per million input tokens and $0.160 per million output tokens, for a blended reference rate of $0.076 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.