LV
LLMversus
Microsoft

Phi-4

Complete specs, pricing, and benchmark data for Phi-4 by Microsoft. Last verified 2026-04-03.

JSON ModeStreaming
Pricing

Input / 1M tokens

$0.070

Output / 1M tokens

$0.140

Cached Input / 1M

$0.018

Context & Output

Context Window

16.384K

Max Output

4,096

TTFT

100ms

Speed

160 tok/s

Benchmarks

Arena ELO

1150

Coding ELO

1130

Reasoning ELO

1140

HumanEval

80

MMLU

80.5

MATH

72

GPQA

45

Price History (Input $/M tokens)

Strengths
  • +Ultra-low cost for a capable model
  • +Strong math for its size (14B params)
  • +Very fast inference
  • +Can run on consumer hardware
Limitations
  • -Small 16K context window
  • -No vision or function calling
  • -Limited compared to larger models on complex tasks

Best For

Cost SensitiveEdge DeploymentMathLightweight Tasks

Compare Phi-4 with...

vs o4-minivs Gemini 2.5 Provs Claude Opus 4vs DeepSeek R1vs o3-minivs Grok 3vs GPT-4.1vs Llama 4 Maverickvs Claude Sonnet 4vs DeepSeek V3vs Gemini 2.0 Flashvs GPT-4o
Official Pricing Page →