LLMversus
Microsoft

Phi-3.5 MoE

Complete specs, pricing, and benchmark data for Phi-3.5 MoE by Microsoft. Last verified 2026-04-20.

JSON ModeFunctionsStreaming
Pricing

Input / 1M tokens

$0.170

Output / 1M tokens

$0.680

Context & Output

Context Window

128K

Max Output

4,096

TTFT

150ms

Speed

100 tok/s

Benchmarks

Arena ELO

1195

Coding ELO

1190

Reasoning ELO

1195

HumanEval

84

MMLU

82

MATH

76

GPQA

40

Try Phi-3.5 MoE API

Start building with Phi-3.5 MoE

Get API Access→

Price History (Input $/M tokens)

Strengths
  • +Mixture of experts
  • +Efficient
  • +Balanced performance
Limitations
  • -Newer architecture
  • -Not widely proven

Best For

General PurposeCost Effective

Compare Phi-3.5 MoE with...

vs Claude Opus 4vs Gemini 2.5 Provs o3vs DeepSeek R1vs o1vs Qwen 3 235B MoEvs Gemini Experimental 1206vs GPT-4.5vs DeepSeek R1 (Groq)vs Llama 4 Maverickvs DeepSeek R1 (Together)vs Grok 3
Official Pricing Page →
Your ad here