prices synced 2026-07-28
M

Phi 4 Mini Instruct

Microsoft · Released Oct 2025

Compare

Phi-4-mini-instruct is a lightweight open model trained on synthetic and curated public data, designed to handle reasoning-heavy tasks efficiently.

Strengths
The model excels at instruction-following and reasoning tasks despite its compact size, making it suitable for resource-constrained deployments.
Best for
Applications requiring on-device inference or cost-efficient processing where reasoning capability matters more than scale.
Limitations
As a smaller model, it may struggle with complex multi-step problems, specialized domain knowledge, or tasks requiring extensive context beyond what training data covered.

Input / 1M

$0.08

Output / 1M

$0.35

Cached input / 1M

$0.08

Context window

128K

Price history

Price per 1M tokens over timeOutput $0.35; Input $0.08 as of Jun 2026.$0$0.1$0.2$0.3$0.4Output on 11 Jun 2026: $0.35Out $0.35Input on 11 Jun 2026: $0.08In $0.08Jun 2026

Snapshots

Effective Input Output Cached in Note Source
11 Jun 2026 $0.08 $0.35 $0.08 Imported from OpenRouter openrouter.ai

More from Microsoft

Report a problem