Phi 4 Mini
Microsoft · dense · 3.8B parameters · 131,072 context
Parameters
3.8B
Context Window
128K tokens
Architecture
Dense
Best GPU
A4000
Cheapest API
$0.35/M
Quality Score
70/100
Intelligence Brief
Phi 4 Mini is a 3.8B parameter DENSE model from Microsoft, featuring Grouped Query Attention (GQA) with 32 layers and 3,072 hidden dimensions. With a 131,072 token context window, it supports tools, structured output, code, math, multilingual, reasoning. On standardized benchmarks, it achieves MMLU 72, HumanEval 55, GSM8K 80. The most cost-effective API deployment is via openrouter at $0.35/M output tokens. For self-hosted inference, A4000 delivers optimal throughput at $161/month.
Provider pricing
1 provider · canonical: openrouter| Provider | Input $/M | Output $/M ▲ | Notes |
|---|---|---|---|
| openroutercanonical | $0.080 | $0.350 | cheapest input · cheapest output |
Prices update via the nightly pricing cron + admin approvals at /admin/ingest-queue. The leaderboard's Input/Output cells show the canonical rate above; this table shows the full spread.
Recent changes
Loading…
Related models
5 suggestions- Phi 1.5Phi · 1.3B—
- Phi 1Phi · 1.3B—
- Phi 2Phi · 2.7B—
- Phi 3.5 MoEPhi · 6.6B$0.300/M out
- Phi-4Phi · 14.7B$0.140/M out
Picks: same family first, then same vendor within ±2× params, then top tag-overlap matches. Price shown is the cheapest Output $/M across providers — the row's page shows the canonical anchor.
Architecture Details
Memory Requirements
BF16 Weights
7.6 GB
FP8 Weights
3.8 GB
INT4 Weights
1.9 GB
GPU Compatibility Matrix
Phi 4 Mini is compatible with 100% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
BF16 · 1 GPU · vllm
100/100
score
Throughput
318.3 tok/s
Latency (ITL)
3.1ms
Est. TTFT
1ms
Cost/Month
$161
Cost/M Tokens
$0.19
BF16 · 1 GPU · vllm
100/100
score
Throughput
509.4 tok/s
Latency (ITL)
2.0ms
Est. TTFT
0ms
Cost/Month
$304
Cost/M Tokens
$0.23
BF16 · 1 GPU · vllm
100/100
score
Throughput
358.1 tok/s
Latency (ITL)
2.8ms
Est. TTFT
0ms
Cost/Month
$237
Cost/M Tokens
$0.25
Deployment Options
API Deployment
openrouter
$0.35/M
output tokens
Single GPU
A4000
$161/mo
Min VRAM: 4 GB
Multi-GPU
RTX 3070 x2
454.5 tok/s
TP· $171/mo
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| openrouter | $0.08 | $0.35 | Cheapest |
Cost Analysis
| Provider | Input $/M | Output $/M | ~Monthly Cost |
|---|---|---|---|
| openrouterBest Value | $0.08 | $0.35 | $2 |
Cost per 1,000 Requests
Short (500 tok)
$0.11
via openrouter
Medium (2K tok)
$0.44
via openrouter
Long (8K tok)
$1.34
via openrouter
Performance Estimates
Throughput by GPU
VRAM Breakdown (A4000, BF16)
Precision Impact
bf16
7.6 GB
weights/GPU
~318.3 tok/s
fp8
3.8 GB
weights/GPU
int4
1.9 GB
weights/GPU
Quality Benchmarks
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy Phi 4 Mini
Self-Hosted Infrastructure
Similar Models
Phi 2
2.7B params · dense
Quality: 50
Phi 1.5
1.3B params · dense
Quality: 38
Phi 1
1.3B params · dense
Quality: 38
Phi 3 Mini 3.8B
3.8B params · dense
Quality: 64
Minitron 4B
4B params · dense
Quality: 50
from $0.06/M
Frequently Asked Questions
How much VRAM does Phi 4 Mini need for inference?
Phi 4 Mini requires approximately 7.6 GB of VRAM at BF16 precision, 3.8 GB at FP8, or 1.9 GB at INT4 quantization. Additional VRAM is needed for KV-cache (65536 bytes per token) and activations (~0.50 GB).
What is the best GPU for Phi 4 Mini?
The top recommended GPU for Phi 4 Mini is the A4000 using BF16 precision. It achieves approximately 318.3 tokens/sec at an estimated cost of $161/month ($0.19/M tokens). Score: 100/100.
How much does Phi 4 Mini inference cost?
Phi 4 Mini API inference starts from $0.08/M input tokens and $0.35/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.