modelbenchmark.io

Phi-4-mini

Microsoft · phi-4-mini

Compare

Efficient model for low-latency assistance, extraction, and routine automation

Specification

most-agreed values

Context
128K
Max output
4K
Released
2024-12-11
Knowledge cutoff
2023-10
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.075
Output
$0.30

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
azure$0.075$0.30128K4K
azure-cognitive-services$0.075$0.30128K4K

Other listings of this model

this page is one of them

The corpus files Phi-4-mini under several keys. This page is the phi-4-mini listing. The full record — every host, every price and every benchmark score — is on the main Phi-4-mini page.

More from Microsoft

most-hosted first