AI TOOLS RADAR
Submit
All models / MICROSOFT
microsoft logo
microsoft

Microsoft: Phi 4

Source description (English)

Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
16,384 tokens
Maximum output
14,745 tokens
Architecture
text->text
Tokenizer
Other
Knowledge cutoff
2024-06-30
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.07
per 1M tokens
Output
$0.14
per 1M tokens
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"microsoft/phi-4","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
text
Output
text
API

Supported API parameters

frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_p
Available providers

1 Provider

Checked: September 7, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

DeepInfra

bf16
Context
16K
Maximum output
15K
Input
$0.07
Output
$0.14
Cache read
Not provided
Cache write
Not provided
microsoft

4 models

All models
microsoft logomicrosoft

Microsoft AI: MAI-Image-2.6

MAI-Image-2.6 is an image generation and editing model from Microsoft AI, the precision tier of the MAI-Image-2.6 family alongside the faster MAI-Image-2.6 Flash. It is suited for design-ready visuals and...

Context
4K
Input
text · image
Output
image
Input: $5 per 1M tokensImage output: $38 per 1M tokens
View model details →
microsoft logomicrosoft

Microsoft AI: MAI-Image-2.6 Flash

MAI-Image-2.6 Flash is the lower-latency, lower-cost member of the MAI-Image-2.6 family from Microsoft AI, built for latency-sensitive, high-throughput production image generation and editing at comparable quality to the precision tier....

Context
4K
Input
text · image
Output
image
Input: $1.75 per 1M tokensImage output: $19 per 1M tokens
View model details →
microsoft logomicrosoft

Microsoft AI: MAI-Transcribe 2

MAI-Transcribe 2 is a multilingual speech-to-text model from Microsoft AI, ranked #1 on the FLEURS multilingual benchmark. It supports 60 languages with automatic language identification, code switching for mixed-language speech,...

Context
Not provided
Input
audio
Output
transcription
Audio seconds: $0.1 per hour
View model details →
microsoft logomicrosoft

Microsoft AI: MAI-Image-2.5 Pro

Microsoft AI's MAI-Image-2.5 is a high-quality image generation model available via Azure AI Foundry. It produces photorealistic and artistic images from text prompts with support for various aspect ratios.

Context
4K
Input
text · image
Output
image
Input: $5 per 1M tokensImage output: $108 per 1M tokens
View model details →