by Microsoft

Phi-4.

text open weights laptop+ 15B params 16K ctx
Cheapest input
$0.07/M
on DeepInfra
Cheapest output
$0.14/M
on DeepInfra
Smallest GPU
1× NVIDIA Tesla T4
$0.019/hr

Phi-4 is Microsoft Research's 14B MIT-licensed text model with a 16K-token context, for memory- and latency-limited uses, focused mainly on English.

Smallest GPU to run it See all quantisations →

1× NVIDIA Tesla T4 · $0.019/hr.

Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
DeepInfra hosted inference $0.07 $0.14 Launch ↗
OpenRouter api aggregator $0.07 $0.14 Launch ↗
Sources

Official references.

FAQ

Frequently asked.

How do I run Phi-4?
Phi-4 is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access Phi-4?
Phi-4 is available via DeepInfra, OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Phi-4?
API pricing starts at $0.07/M input tokens and $0.14/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Phi-4 open-source or proprietary?
Phi-4 is open-weight under the MIT license. You can download and self-host it.