Modeldex
Drag to turnCard front showing

MicrosoftTextCommon

Phi-4-multimodal

Multimodal model for analyzing text, images, documents, and rich media

phi-4-multimodal
Type
Text
Quality
Not rated yet
Context window
128,000 tokens
Max output
4,096 tokens
Input price
$0.08 / 1M tokens
Output price
$0.32 / 1M tokens
Cache read
—
Cache write
—
Parameters
5.6B (5,574,460,384)
Downloads
140K in the last 30 days
Likes
1.6K
Access to weights
Open download
Released
Dec 11, 2024
Knowledge cutoff
Oct 2023
Takes in
Text, Image, Audio
Puts out
Text
Reasoning
No
Tool calling
No
Structured output
No
File attachments
Yes
Access
Open weights
License
MIT
Rarity
Common
Set number
456/1044
Open Microsoft docsWeights on Hugging FaceWhere to run it 4Evolution 3/3Meet its creatureBattle Step 3.5 Flash 2603

License read from the model’s Hugging Face card. Specs from models.dev, downloads from Hugging Face, last changed Oct 19, 2026. Official source: learn.microsoft.com.

How good is it?

Public leaderboard scores for Phi-4-multimodal, refreshed daily from Epoch AI and LMArena.

No public leaderboard lists Phi-4-multimodal yet. Epoch AI and LMArena cover most chat, image, and video models from the big labs; embeddings, speech, and small open models mostly go unrated.

Where to run it

4 providers sell Phi-4-multimodal through an API. Prices are per million tokens, cheapest first.

API providers

ProviderInputOutputContext
NvidiaFreemicrosoft/phi-4-multimodal-instructFreeFree128K
NanoGPTCheapest paidphi-4-multimodal-instruct$0.07$0.11128K
AzureOfficialphi-4-multimodal$0.08$0.32128K
Azure Cognitive Servicesphi-4-multimodal$0.08$0.32128K

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current text models from other labs at a similar output price.

More from Microsoft

Microsoft

harrier-oss-v1-270m

SIZE268M
Embedding
TextDownloads130K/mo
–Likes210

Embedding model from Microsoft, 268M parameters.

Open weightsMIT843/1044
Microsoft

harrier-oss-v1-0.6b

SIZE596M
Embedding
TextDownloads280K/mo
–Likes320

Embedding model from Microsoft, 596M parameters.

Open weightsMIT842/1044
Microsoft

VibeVoice-ASR

SIZE8.7B
Speech to text
AudioDownloads690K/mo
TextLikes1.3K

Speech recognition model from Microsoft, 8.7B parameters.

Open weightsMIT757/1044
Microsoft

VibeVoice-Realtime-0.5B

SIZE1B
Text to speech
TextDownloads290K/mo
AudioLikes1.3K

Text-to-speech model from Microsoft, 1B parameters.

Open weightsMIT719/1044
Microsoft

TRELLIS.2-4B

3D generation
ImageDownloads2.3M/mo
–Likes1.4K

Image-to-3D model from Microsoft.

Open weightsMIT712/1044
Microsoft

VibeVoice-1.5B

SIZE2.7B
Text to speech
TextDownloads540K/mo
AudioLikes2.5K

Text-to-speech model from Microsoft, 2.7B parameters.

Open weightsMIT644/1044
Microsoft

Phi-4-reasoning-plus

CTX32K
Reasoning
TextInput$0.13/M
TextOutput$0.50/M

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Open weightsMIT458/1044
Microsoft

Phi-4-reasoning

CTX32K
Reasoning
TextInput$0.13/M
TextOutput$0.50/M

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Open weightsMIT457/1044
Deck0/4
  1. Empty slot
  2. Empty slot
  3. Empty slot
  4. Empty slot