Microsoft

Phi-4

Vérifié par l’équipe de recherche de GetInfoUsDernière révision : October 2026Politique éditoriale
80
Intelligence Index

de Microsoft 14B à poids ouverts modèle trained extensively sur élevé-qualité synthetic datasets à deliver mathématiques et codage density rivaling grand modèles.

Technical Specifications

Provider
Microsoft
Category
open-source
Release Date
2024-12
Knowledge Cutoff
June 2024
Architecture
Synthetic-Data Dense Reasoning Transformer
Parameters
14B
Context Window
16K tokens
Max Output
4K tokens
Cached Input Price
$0 / 1M tokens
Batch API Discount
Standard rate
Consumer Subscription
Free / Self-Hosted
Reasoning Mode
Yes (Chain-of-Thought)
Reasoning Effort Control
Fixed
Tool Calling
Yes
Structured Outputs
Yes
Open Weights
Yes (Open Source / Self-Hostable)
Input Modalities
text
Output Modalities
text
Official Documentation
Visit Official Docs ↗

Data Privacy, Licensing & Deployment Governance

API Data Training Policy
100% Isolated when self-hosted on private GPUs or VPC
Model License & Commercial Rights
Open-Weights Research & Commercial License
Deployment & Cloud Availability
Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API
Output Ownership
Full commercial ownership of generated outputs

Official Provider Release Intelligence, API Quotas & Agentic Specs

Compare Multi-Models Side-by-Side →
Official API Model ID (SDK String)
phi-4
Supported SDK & API Protocol
OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
Lifecycle & Deprecation Status
Legacy Stable (Upgrade path available in Microsoft lineup)
Production Rate Limits (RPM & TPM)
Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud
Long-Context Pricing Tier (>128K / >200K)
Free across full context window (only KV-cache VRAM scales)
Prompt Cache Write & TTL Policy
Automatic prefix KV-caching in vLLM / SGLang (0 cost)
Computer Use & Browser GUI Agent
API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop)
MCP & Parallel Tool Calling
Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
Web Search Grounding & Code Sandbox
Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools
Fine-Tuning & Distillation Support
Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory)
Multimodal Tokenization Billing
Text BPE (~4 chars/token)
Weights Precision & Quantization
BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0)
Minimum GPU VRAM Requirement
9 GB VRAM (4-bit Quantized) · 30 GB VRAM (Native BF16)
Supported Inference Engines
vLLM, SGLang, Ollama, llama.cpp, TensorRT-LLM, HuggingFace TGI
System Card & Safety Framework
Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma)
Enterprise Compliance (SOC2 / HIPAA / ZDR)
100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control
Engineering & Pricing Workbench

Phi-4 Cost, Context, Hardware & API Integration

500 / day
4,000 tok
1,000 tok
Conversation Depth (History Re-billing):1 Turn (Single-Shot)
50%
Estimated Monthly API Cost (30 Days)
Free ($0)
Subscription ($20/mo) vs API

Open-weights or free-tier model: $0 API license cost when self-hosted.

Same Monthly Workload Cost Across Popular Reference Models

Phi-4 (Active)
$0.00
/ month
Gemini 2.5 Flash
$18.00
/ month
DeepSeek V3
$32.70
/ month
GPT-4o
$300.00
/ month
Claude 3.7 Sonnet
$405.00
/ month

Live Prompt Paste Tokenizer & Cost Counter

Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.

Chars / Words
175 / 24
OpenAI o200k
~46 tok
Claude BPE
~49 tok
Llama / DeepSeek
~51 tok

Hybrid Prompt Routing Cascade Simulator

Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to Phi-4:

Cascaded Monthly Bill:$13.50/mo
This model is already priced at or below the fast router baseline.

Benchmark Scores & 6-Axis Capability Radar

Benchmark Encyclopedia
Coding (88)Reasoning (63)Knowledge (79)Speed (90)Context (55)Cost Value (98)
Phi-42026 Frontier Median
GPQA Diamond
55%
MMLU-Pro
78.5%
HumanEval
88%
Chatbot Arena Elo
1305pts

Strengths

  • Remarkable STEM et codage performances packed dans un compact 14B paramètre empreinte
  • Easily deployable sur unique desktop GPUs (RTX 4070/4080) et Apple Silicon Macs
  • à poids ouverts avec permissive MIT licensing

Limitations & Trade-offs

  • Relatively compact 16K fenêtre de contexte limits grand document ingestion
  • Max sortie tokens capped à 4096 tokens

Editorial Assessment

de Microsoft masterclass dans petit modèle de langage efficacité, proving qui données qualité triumphs sur échelle.

Best for: local périphérie développeur assistants, offline mathématiques problem-solving, et efficient workstation tâches

Frequently Asked Questions about Phi-4

How much does the Phi-4 API cost per 1M tokens?+

Phi-4 by Microsoft is priced at $0 per 1M input tokens and $0 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0 per 1M tokens, and asynchronous Batch API requests receive a 0% discount.

Should I use a $20/month subscription or the Phi-4 pay-as-you-go API?+

A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.

How many words and pages fit in Phi-4's context window?+

Phi-4 features a 16K tokens context window, which equals approximately 12,288 English words or ~33 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 4,096 tokens.

Can I run Phi-4 locally on my own GPU (Open Weights)?+

Yes, Phi-4 (14B) releases open weights that can be self-hosted locally or on private cloud GPUs using vLLM, Ollama, SGLang, or llama.cpp.

Does Microsoft train on data sent to the Phi-4 API, and is commercial use allowed?+

100% Isolated when self-hosted on private GPUs or VPC. License tier: Open-Weights Research & Commercial License. Full commercial ownership of generated outputs. Supported deployment channels include: Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API.

How does Phi-4 perform on coding and reasoning benchmarks?+

Phi-4 achieves a composite Intelligence Index of 80/100, scoring N/A% on SWE-bench Verified, 55% on GPQA Diamond, 78.5% on MMLU-Pro, and 1305 pts on Chatbot Arena Elo.

What is Phi-4 best used for?+

Phi-4 is best suited for: local périphérie développeur assistants, offline mathématiques problem-solving, et efficient workstation tâches. Assessment: de Microsoft masterclass dans petit modèle de langage efficacité, proving qui données qualité triumphs sur échelle.

Microsoft Family Lineage, Routing Tiers & Upgrade Path

Step down to a lighter sibling for high-volume routing or step up to Microsoft's flagship reasoning tier:

Les scores de benchmarks, tarifs par token et limites évoluent rapidement. Vérifiez toujours les spécifications actuelles sur la documentation officielle du fournisseur.

Sources: Microsoft Research Phi-4 Technical Report & Hugging Face↗