Last refreshed 2026-05-01. Next refresh: weekly.
Why use Phi-4 Mini Flash Reasoning on NVIDIA NIM?
NVIDIA NIM offers Phi-4 Mini Flash Reasoning with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Input / 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-flash-reasoningModel ID
microsoft/phi-4-mini-flash-reasoningRequest example
Curated snippets for this provider are not sourced yet. Use NVIDIA NIM documentation with model ID
microsoft/phi-4-mini-flash-reasoning.Gotchas
- Use provider model ID "microsoft/phi-4-mini-flash-reasoning", not the LLMReference slug "phi-4-mini-flash-reasoning".
Pricing
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
Capabilities
Reasoning
About Phi-4 Mini Flash Reasoning
Lightweight reasoning variant of Microsoft Phi-4 Mini optimized for fast inference.
FAQ
What is the context window for Phi-4 Mini Flash Reasoning on NVIDIA NIM?
Phi-4 Mini Flash Reasoning supports a 128,000 token context window on NVIDIA NIM.
What API model ID do I use for Phi-4 Mini Flash Reasoning on NVIDIA NIM?
Use the model ID microsoft/phi-4-mini-flash-reasoning when calling NVIDIA NIM's API.
Who created Phi-4 Mini Flash Reasoning?
Phi-4 Mini Flash Reasoning was created by Microsoft Research as part of the Phi-4 model family.
Is Phi-4 Mini Flash Reasoning open source?
Phi-4 Mini Flash Reasoning is open source according to the seed data.
Model Specs
Released2025-12-01
Context128K
ArchitectureDecoder Only