Last refreshed 2026-05-01. Next refresh: weekly.
Why use Phi-4 Mini on NVIDIA NIM?
NVIDIA NIM offers Phi-4 Mini with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Compare Phi-4 Mini across 3 providers to find the best fit for your use caseInput / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: microsoft/phi-4-mini-instructModel ID
microsoft/phi-4-mini-instructRequest example
Curated snippets for this provider are not sourced yet. Use NVIDIA NIM documentation with model ID
microsoft/phi-4-mini-instruct.Gotchas
- Use provider model ID "microsoft/phi-4-mini-instruct", not the LLMReference slug "phi-4-mini".
Compare Phi-4 Mini Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Fireworks AI | $0.90 | $0.90 |
| NVIDIA NIM | — | — |
| Novita AI | $0.05 | $0.15 |
Pricing
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
| GPU Config | 1xH100 |
Capabilities
No model capability flags are currently sourced.
About Phi-4 Mini
Phi-4 family model from Microsoft Research. Mini variant with efficient performance.
FAQ
How does NVIDIA NIM compare to other Phi-4 Mini providers?
Phi-4 Mini is available from 3 providers. The cheapest input pricing is $0.05/1M tokens from Novita AI.
What API model ID do I use for Phi-4 Mini on NVIDIA NIM?
Use the model ID microsoft/phi-4-mini-instruct when calling NVIDIA NIM's API.
Who created Phi-4 Mini?
Phi-4 Mini was created by Microsoft Research as part of the Phi-4 model family.
Is Phi-4 Mini open source?
Phi-4 Mini is open source according to the seed data.
Model Specs
Released2024-12-13
Parameters3.8B