Atlas / Models / Microsoft / Microsoft: Phi 4

Microsoft: Phi 4✓ Catalog verified

microsoft/phi-4

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 parameters, it was trained on a mix of high-quality synthetic datasets, data from curated websites, and academic materials. It has undergone careful improvement to follow instructions accurately and maintain strong safety standards. It works best with English language inputs. For more information, please see Phi-4 Technical Report

Input price
$0.07 /1M
Output price
$0.14 /1M
Context
16K
Modalities
text
Released
Jan 10, 2025
Tool calling
Atlas signal
78/100
01

Overview

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 parameters, it was trained on a mix of high-quality synthetic datasets, data from curated websites, and academic materials. It has undergone careful improvement to follow instructions accurately and maintain strong safety standards. It works best with English language inputs. For more information, please see Phi-4 Technical Report

Access: available through the official Microsoft API. Context window: 16K.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Aug 5, 2026
02

Specifications

API identifiermicrosoft/phi-4
ProviderMicrosoft
Model typeText LLM
Context window16K catalog
Input modalitiestext
Output modalitiestext
ReleasedJan 10, 2025
ModeratedNo
Architecture modalitytext->text
Supported parameters
frequency_penaltylogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_logprobstop_p
Source: provider documentation + catalog feedMethodology →
03

Pricing

Live pricing components for microsoft/phi-4 as published in the catalog.

$0.07
Input /1M
$0.14
Output /1M
Per request
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$6.5e-8$0.07 / 1MPer input token
Completion tokens$1.4e-7$0.14 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search feeN/AN/APer search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$0.06Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual UnderstandingNot advertisedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool CallingNot advertisedSupports tools / function calling
Self-HostingNot advertisedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

Microsoft: Phi 4
MMLU Signal (Reasoning)
80signal
Coding Signal (HumanEval proxy)
77signal
Math Signal (GSM8K proxy)
74signal
Science Signal (GPQA proxy)
82signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call Microsoft: Phi 4 through an OpenAI-compatible client.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="microsoft/phi-4",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does Microsoft: Phi 4 cost?

$0.07 per 1M input tokens and $0.14 per 1M output tokens on the official Microsoft API.

What is the context window of Microsoft: Phi 4?

Microsoft: Phi 4 supports up to 16K tokens of context.

Does Microsoft: Phi 4 support tool / function calling?

Microsoft: Phi 4 does not advertise first-class tool/function calling. Check vendor docs for the latest capabilities.

How do I access Microsoft: Phi 4?

Use the official Microsoft API with the model id `microsoft/phi-4`. See the Quick start section above for code examples.