modelbenchmark.io

Phi 4 Mini

Microsoft · phi-4-mini-instruct

Compare

Compact GPT model for low-latency assistance and high-volume workloads

2 figures withheld: the value failed a range check.

Specification

most-agreed values

Context
128K
Max output
16K
Released
2025-07-26
Knowledge cutoff
2024-12
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.17
Output
$0.68
Cache read
$0.085

Available from 4 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nvidiafreefree131K8K
azure_ai$0.075$0.30131K4K
nano-gpt$0.17$0.68$0.085128K16K
wandb · wandb128K128K

Other listings of this model

same model, different key

More from Microsoft

most-hosted first