Using Phi-3 Small 8K on NVIDIA NIM

Implementation guide · Phi-3 · Microsoft Research

ProvisionedOpen Source

NVIDIA NIM exposes Phi-3 Small 8K through model ID phi-3-small-8k. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-05-19. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at NVIDIA NIM and generate an API key.
  2. 2
    Use the NVIDIA NIM SDK or REST API to call phi-3-small-8k — see the documentation for request format.
  3. 3
    You'll be billed . See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See NVIDIA NIM documentation for integration details.

Pricing on NVIDIA NIM

Capabilities

No model capability flags are currently sourced.

About Phi-3 Small 8K

Phi-3 Small 8K is Microsoft Research's Phi-3 model. It offers an 8K-token context window with weights openly available for self-hosting.

Full model details →

Model Specs

Released2024-05-21
Parameters7B
Context8k
ArchitectureDecoder Only
Knowledge cutoff2023-10

More Models on NVIDIA NIM

Phi-3 Mini 128KPhi-3 Medium 4KPhi-3 Mini 4kPhi-3 Small 128KPhi-3 VisionPhi-3 Medium 128K
All models on NVIDIA NIM →

Also available on(1)

Microsoft Foundry$0.32/1M
Compare all providers →

Provider

NVIDIA NIM

NVIDIA

Santa Clara, California, United States