LV
LLMversus

Phi-4 vs Yi-Large: Pricing, Benchmarks & Verdict (2026)

Pricing verified Apr 8, 2026

⚡ Quick Answer

Compare Phi-4 and Yi-Large across pricing, benchmarks, and capabilities.

Updated: April 8, 2026 · ✓ Pricing verified

Side-by-Side Comparison

FeaturePhi-4Yi-Large
ProviderMicrosoft01.AI
Input Price / 1M tokens$0.065$3.00
Output Price / 1M tokens$0.140$3.00
Context Window
16.384K
32K
Max Output Tokens
4,096
4,096
Arena ELO
1,150
1,185
Coding ELO
1,130
1,195
TTFT (ms)
100
150
Tokens/sec
160
100
MultimodalNoNo
JSON ModeYesYes
Function CallingNoYes
VisionNoNo
When to Use Phi-4

Phi-4 excels at cost-sensitive, edge-deployment, math, lightweight-tasks tasks.

Strengths:

  • Ultra-low cost for a capable model
  • Strong math for its size (14B params)
  • Very fast inference
  • Can run on consumer hardware

Best for:

cost-sensitiveedge-deploymentmathlightweight-tasks
When to Use Yi-Large

Yi-Large excels at general-purpose, coding tasks.

Strengths:

  • Good quality
  • Fast
  • Balanced performance

Best for:

general-purposecoding

Related Comparisons

Claude Opus 4 vs Yi-LargeClaude Opus 4 vs Phi-4Gemini 2 5 Pro vs Yi-LargeGemini 2 5 Pro vs Phi-4O3 vs Yi-LargeO3 vs Phi-4Deepseek R1 vs Yi-LargeDeepseek R1 vs Phi-4O1 vs Yi-LargeO1 vs Phi-4Qwen 3 235b vs Yi-LargePhi-4 vs Qwen 3 235bGemini Exp 1206 vs Yi-LargeGemini Exp 1206 vs Phi-4Gpt 4 5 vs Yi-LargeGpt 4 5 vs Phi-4Groq Deepseek R1 vs Yi-LargeGroq Deepseek R1 vs Phi-4Llama 4 Maverick vs Yi-LargeLlama 4 Maverick vs Phi-4