Microsoft logo

Microsoft: Phi-4-mini

Compact Microsoft instruction model tuned for efficient coding assistance, reasoning, and low-latency agent tasks

Source-linked phi Open weights Released 2024-12-11
API record Report
InputT
OutputT
Input price$0.075/M
Output price$0.3/M
Context128K
Max output4.096K
Providers2
Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price
Providers offering Phi-4-mini
ProviderProvider model IDContextMax outputInputOutputCache readCapabilitiesDocs
Azure Cognitive Services phi-4-mini 128K 4.096K $0.075 $0.3 Tools Docs ↗
Azure phi-4-mini 128K 4.096K $0.075 $0.3 Tools Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.075/M

Across 2 priced providers

Median input $0.075/M

Midpoint of listed rates

Highest input $0.075/M

Same as the lowest listed rate

Output range $0.3 – $0.3

Per million output tokens

Azure Cognitive Services $0.075/M
Azure $0.075/M
Cost calculator

Estimate a workload

$0.00
Excludes taxes, non-token charges, and tiered discounts.

2 providers list the identical $0.075 input rate, so price alone will not separate them — compare context limits, max output, and capabilities above.

Specification

Capabilities

Recorded from the source catalog and provider listings.

× Reasoning No
Tool calling Yes
? Structured output Unknown
× Attachments No
× Vision input No
Open weights Yes
Creator
Microsoft
Model family
phi
Knowledge cutoff
2023-10
License
Not documented
Release date
2024-12-11
Model ID
microsoft/phi-4-mini
Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry
MMLU accuracy Source ↗
67.3 1 model scored — too few for a distribution

Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log
No changes recorded

This record has not changed within the retained import history.

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation
Endpoint
GET https://www.modelbench.lol/api/v1/models/microsoft/phi-4-mini
curl
curl "https://www.modelbench.lol/api/v1/models/microsoft/phi-4-mini"
Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is Phi-4-mini?

Compact Microsoft instruction model tuned for efficient coding assistance, reasoning, and low-latency agent tasks. It is published by Microsoft and catalogued here from Models.dev.

How much does Phi-4-mini cost?

Listed input pricing starts at $0.075 per million tokens from Azure Cognitive Services.

What is the context length of Phi-4-mini?

Phi-4-mini accepts up to 128K tokens of context and returns up to 4.096K output tokens.

Does Phi-4-mini support tool calling and structured output?

Provider catalogs list support for tool calling.

Which providers serve Phi-4-mini?

2 providers list this model: Azure Cognitive Services, Azure.

Are the weights for Phi-4-mini open?

Yes. The weights are published.

When was Phi-4-mini released?

The catalog records a release date of 2024-12-11, last verified Aug 08, 2026.

More models from Microsoft

View all →