modelbenchmark.io

Phi-4-reasoning

Microsoft · phi-4-reasoning

Compare

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Specification

most-agreed values

Context
32K
Max output
4K
Released
2024-12-11
Knowledge cutoff
2023-10
Retires
2027-01-17
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.125
Output
$0.50

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
azure$0.125$0.50——32K4K—
azure_ai$0.125$0.50——33K4K2027-01-17
azure-cognitive-services$0.125$0.50——32K4K—

More from Microsoft

most-hosted first