LLM Reference

Phi-3 Medium 4K

Released
2024-05-21
Last refreshed
2026-06-15
Status
Researched 81d ago
Open sourceCommercial use: permittedCodingClassificationJSON / Tool use

Phi-3 Medium 4K is worth evaluating for coding, classification, and json / tool use when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, classification, and json / tool use
  • Workloads that can use a 4k context window
  • Buyers comparing 3 tracked provider routes

Do not use it for

  • Vision or document-understanding workloads
Specifications
Family
Phi-3
Released
2024-05-21
Context
4k
Parameters
14B
Architecture
Decoder Only
Knowledge cutoff
2023-10
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
$0.410
Input / 1M
$0.140

Cheapest of 3 routes · DeepInfra

About

The Phi-3 Medium 4K, developed by Microsoft, is a state-of-the-art large language model with 14 billion parameters. It is engineered for efficiency across various tasks, particularly excelling in reasoning capabilities. This model is designed to handle 4,096 token context lengths, allowing for the processing of longer input sequences. Leveraging a dense, decoder-only Transformer architecture, it incorporates techniques like supervised fine-tuning and direct preference optimization to align with human preferences and safety standards. The model supports multilingual data, although it is primarily trained in English. Its lightweight nature allows for deployment on diverse hardware platforms, making it accessible and versatile for both commercial and research purposes. Safety measures are embedded, although further precautions are advised for applications with higher risks.

Phi-3 Medium 4K is an open-source model in the Phi-3 family. The structured metadata tracks a 4k-token context window and structured outputs. This page tracks provider routes through Microsoft Foundry, NVIDIA NIM, and DeepInfra, with the cheapest tracked route listed at $0.14 input and $0.41 output per 1M tokens. Headline tracked benchmarks include HumanEval 52.7 and Massive Multitask Language Understanding 68.9.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ C

1 relevant benchmark in the decision map.

Classification

Q/$ C

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
DeepInfra$0.140$0.410
Serverless
Microsoft Foundry$0.450$1.35
ServerlessProvisioned
NVIDIA NIM--
ProvisionedPartial

Available via routers & gateways(6)

Capabilities

Structured Outputs

Benchmark peer barsfor Coding

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.
BenchmarkScoreVersionSource
HumanEval52.7pass@1https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard
Massive Multitask Language Understanding68.95-shothttps://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard

Migration checks

No linked migration route is available for this model yet.

Frequently asked questions

What is the context window of Phi-3 Medium 4K?

Phi-3 Medium 4K has a context window of 4k tokens.

How much does Phi-3 Medium 4K cost?

Phi-3 Medium 4K pricing ranges from $0.14/1M to $0.45/1M input tokens depending on the provider.

When was Phi-3 Medium 4K released?

Phi-3 Medium 4K was released on 2024-05-21.

Which providers offer Phi-3 Medium 4K?

Phi-3 Medium 4K is available from 3 providers: Microsoft Foundry, NVIDIA NIM, DeepInfra.

What benchmarks has Phi-3 Medium 4K been tested on?

Phi-3 Medium 4K has been evaluated on 2 benchmarks, including HumanEval, Massive Multitask Language Understanding.