Last refreshed 2026-10-05. Next refresh: weekly.
Why use Phi-3 Vision on NVIDIA NIM?
NVIDIA NIM offers Phi-3 Vision. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Compare Phi-3 Vision across 3 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: microsoft/phi-3-vision-128k-instructmicrosoft/phi-3-vision-128k-instructRequest example
microsoft/phi-3-vision-128k-instruct.Gotchas
- Use provider model ID "microsoft/phi-3-vision-128k-instruct", not the LLMReference slug "phi-3-vision".
Compare Phi-3 Vision Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Microsoft Foundry | $0.28 | $0.84 |
| Fireworks AI | $0.20 | $0.20 |
| NVIDIA NIM | — | — |
Capabilities
About Phi-3 Vision
Phi-3 Vision is a sophisticated multimodal AI model from Microsoft, designed to adeptly integrate language and vision capabilities. Unlike traditional language models, it processes both text and images and can perform tasks such as optical character recognition, chart analysis, and image interpretation. Its architecture features an image encoder, a text-image connector, a projector for mapping image features, and the Phi-3 Mini language model. Despite its relatively small size of 4.2 billion parameters, it competes with larger models and suits devices with limited computational power. Phi-3 Vision's ability to handle up to 128K tokens supports complex multimodal reasoning.