LLM Reference

Phi-4 14B

Released
2024-12-13
Last refreshed
2026-06-15
Status
Researched 60d ago
Open sourceCommercial use: permittedClassificationJSON / Tool use

Phi-4 14B is worth evaluating for classification and json / tool use when its provider route and context window match the workload.

Use it for

  • Teams evaluating classification and json / tool use
  • Workloads that can use a 16k context window
  • Buyers comparing 3 tracked provider routes

Do not use it for

  • Vision or document-understanding workloads
Specifications
Family
Phi-4
Released
2024-12-13
Context
16k
Parameters
14B
Architecture
Decoder Only
Knowledge cutoff
2024-06
Specialization
general
Openness
Open source
License
MITOSI-approvedCommercial use: permitted
Weights
Unknown
Code
Unknown
Training
Fine-tuned
Created by

Advancing the state-of-the-art in AI and computing.

Redmond, Washington, United States
Founded 1991
Website
Pricing
Output / 1M
$0.140
Input / 1M
$0.065

Cheapest of 3 routes · OpenRouter

About

Phi-4 14B is Microsoft Research's Phi-4 model. Weights are openly available for self-hosting and scores 56.1 on GPQA.

Phi-4 14B is an open-source model in the Phi-4 family. The structured metadata tracks a 16k-token context window and structured outputs. This page tracks provider routes through OpenRouter, Fireworks AI, and Microsoft Foundry, with the cheapest tracked route listed at $0.065 input and $0.14 output per 1M tokens. Headline tracked benchmarks include Google-Proof Q&A 56.1 and Massive Multitask Language Understanding 84.8.

Top use-case fit

Classification

Q/$ A

1 relevant benchmark in the decision map.

JSON / Tool use

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare all 3

Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
OpenRouter$0.065$0.140
Serverless
Fireworks AI$0.900$0.900
Serverless
Microsoft Foundry--
ServerlessPartial

Available via routers & gateways(6)

Capabilities

Structured Outputs

Benchmark peer barsfor Classification

Benchmark scores(2)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
Google-Proof Q&A56.1Observed 2026-04-28Source
Massive Multitask Language Understanding84.8Observed 2026-04-28Source

Migration checks

No linked migration route is available for this model yet.

Compare Phi-4 14B with other models

Frequently asked questions

What is the context window of Phi-4 14B?

Phi-4 14B has a context window of 16k tokens.

How much does Phi-4 14B cost?

Phi-4 14B pricing ranges from $0.065/1M to $0.9/1M input tokens depending on the provider.

When was Phi-4 14B released?

Phi-4 14B was released on 2024-12-13.

Which providers offer Phi-4 14B?

Phi-4 14B is available from 3 providers: OpenRouter, Fireworks AI, Microsoft Foundry.

What benchmarks has Phi-4 14B been tested on?

Phi-4 14B has been evaluated on 2 benchmarks, including Google-Proof Q&A, Massive Multitask Language Understanding.