As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/phi-4-reasoning-vision-15b/

# Phi-4-Reasoning-Vision-15B

Microsoft, Phi-4 family. Status: current. Type: multimodal model. Released: 2026-03-04. Training cutoff: not published.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face |  |  | https://huggingface.co/microsoft/Phi-4-reasoning-vision-15B |
| Microsoft Foundry |  |  | https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-phi-4-reasoning-vision-to-microsoft-foundry/4499154 https://aka.ms/Phi-4-r-v-foundry |

## Pricing

- Price not published.
- Last checked: 2026-09-29

## Specs

- Input: text, image
- Output: text
- Context window: 16,384 tokens
- Max output: not published
- Open weights: yes
- Licence: mit

## What it has not seen

- No published training cutoff. Counted from its release (2026-03-04): at least 1,916 AI events since (438 major, 85 historic), as of 2026-11-13.
- Everything since February 2026: https://postcutoff.com/since/2026-02/

## What stands out

- Hybrid think / no-think vision reasoning: Automatically chooses direct answers for perception tasks and long chain-of-thought only for math/science/diagram problems. Source: https://huggingface.co/microsoft/Phi-4-reasoning-vision-15B
- GUI grounding for computer-use agents: Dynamic-resolution SigLIP-2 encoder (up to 3,600 visual tokens) with strengths in GUI grounding for computer-use agents. Source: https://huggingface.co/microsoft/Phi-4-reasoning-vision-15B

## Notes

Newest Phi model found (Mar 2026). Foundry model id and pricing not verified. Microsoft MAI models (MAI-Image-2/2.5, MAI-Voice-2, MAI-Transcribe-2, MAI-Thinking-1) are in Foundry but not covered by a file here.

Compact open multimodal reasoning model for visual math/science and screen understanding.

```python
from transformers import AutoProcessor, AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-4-reasoning-vision-15B", trust_remote_code=True, device_map="auto")
```

Sources: https://huggingface.co/microsoft/Phi-4-reasoning-vision-15B

Model page: https://postcutoff.com/m/phi-4-reasoning-vision-15b/