PikaAINewsPikaAINews
Subscribe
All Models
MicrosoftactiveOpen Source

Phi-4-Reasoning

phi-4-reasoning

14B reasoning model trained with SFT + DPO on chain-of-thought data.

Context Window

32.8K

tokens

Max Output

4.1K

tokens

Input Price

—

per 1M tokens

Output Price

—

per 1M tokens

Details

Familyphi
Parameters14B
Training Cutoff2025-01-01
ReleasedApril 30, 2025

Capabilities

FunctionsStreamingCodeReasoning
Documentation

Evaluation Scores(5 benchmarks)

MATH-500
75%
HumanEval
70%
MMLU-Pro
58%
GPQA Diamond
48%

Quick Access

curl pikaainews.com/api/models/microsoft-phi-4-reasoning
npx pika-models info microsoft-phi-4-reasoning

Get API Access

Third-Party Providers & Aggregators

DeepInfra

Lowest per-token rates for open-source models.

Fireworks AI

Fastest inference engine. Multimodal support, HIPAA/SOC2.

Together AI

Fast open-source model inference. Sub-100ms latency.

Other phi models

Microsoft

Phi-4-Mini

phi-4-mini

128K ctx
Microsoft

Phi-4

phi-4

16.4K ctx
Microsoft

Phi-3.5 MoE

phi-3.5-moe

131.1K ctx
Microsoft

Phi-3.5 Mini

phi-3.5-mini

131.1K ctx
Microsoft

Phi-3 Medium

phi-3-medium

131.1K ctx
Microsoft

Phi-3 Mini

phi-3-mini

128K ctx