Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Text

Phi 4 Multimodal

Phi 4 by Microsoft. A small multimodal model that can handle images and text.

Added Jul 26, 2025

Pricing

Auto routing · per 1M tokens
Input
$0.07
Output
$0.11
Cache read
$0.035
Compare provider prices

Specifications

Context window
128K
Max output
16.4K
Parameters
5.6B

Benchmarks

Leaderboard results

BenchmarkScoreRank on NanoGPT
EQ-Bench

EQ-Bench data, MIT · Updated Nov 13, 2026

Longform Writing

22.8

#96 of 97

Filtered and ranked to models on NanoGPT.

Providers

Provider information for this model’s automatic routing. These routes cannot be selected individually.

Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)

Auto
Auto
Recommended
$0.07$0.11$0.035N/AN/A
Parasail
Parasail
US
$0.07$0.11$0.035N/AN/A
Privacy:ZDR, prompts not retained

Related text models

Compare Phi 4 Multimodal with similar models from the same provider or model family.

Phi 4 Mini

phi-4-mini-instruct

Phi 4 Mini by Microsoft. A small multilingual model.

WizardLM-2 8x22B

microsoft/wizardlm-2-8x22b

Microsoft's advanced Wizard model. The most popular role-playing model.

Bielik 11B v3.0

speakleash/bielik-11b-v3.0-instruct

SpeakLeash’s Polish-focused multilingual model for conversation, writing and text analysis across European languages. Supports tool calling with a 32K context window.

Mistral Small 3 24B (2501)

mistralai/mistral-small-24b-instruct-2501

Mistral Small 3 24B (2501) hosted by IONOS in Berlin, Germany. Zero data retention.

Gemma 4 12B Instruct

gemma-4-12b-it

Google's Gemma 4 12B Instruct is an open-weight multimodal model for text and image understanding, with tool calling and structured output support.

Gemma 4 E2B Instruct

gemma-4-e2b-it

Google's Gemma 4 E2B Instruct is a compact open-weight multimodal model with 2B active parameters, supporting text, image, audio, video, tools, and structured output.