Phi 4 Official Specifications, Pricing & Benchmarks
Phi 4 (phi-4) by Microsoft, released 2025-01-10, featuring 16,384 context window, 14,745 max output tokens, and Text input.
📋 Phi 4 Official API & System Card Specifications
Verified against official Microsoft developer documentation & pricing
1. Identity & Capabilities
API Spec- API Model ID
- phi-4
- Release Date
- 2025-01-10
- Weight License
- Open-Weight (API Spec)
- Native Reasoning
- —
- Function Calling & JSON Schema
- 部分支持
- Batch API 异步批处理
- ✅ Supported (50% off)
2. Context, Output & Modalities
Limits- Max Context Window
- 16,000 tokens (16K)
- Max Output Tokens
- 14,745 tokens
- Input Modalities
- Text
- Output Modalities
- Text
- Direct China Access
- 🌐 Global / OpenRouter
- Deployment Mode
- Open-Weight + Cloud API
3. Official Pricing & Cache
USD / 1M- Input / 1M Tokens
- $ 0.07
- Cached Input / 1M
- $ 0.014 -80%
- Output / 1M Tokens
- $ 0.14
🎛️ Official Sampling & Reasoning Parameters
Recommended generation settings & API parameter constraints
📊 Phi 4 Full Benchmark Scorecard
13 public benchmarks · ranks among 154 models · synced 2026-11-20
📐 Math 7 items
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains.
MGSM (Multilingual Grade School Math) is a benchmark of grade-school math problems. Contains 250 grade-school math problems manually translated from the GSM8K dataset into ten typologically diverse languages: Spanish, French, German, Russian, Chinese, Japanese, Thai, Swahili…
MATH dataset contains 12,500 challenging competition mathematics problems from AMC 10, AMC 12, AIME, and other mathematics competitions.
DROP (Discrete Reasoning Over Paragraphs) is a reading comprehension benchmark requiring discrete reasoning over paragraph content.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks.
PhiBench is an internal benchmark designed to evaluate diverse skills and reasoning abilities of language models, covering a wide range of tasks including coding (debugging, extending incomplete code, explaining code snippets) and mathematics (identifying proof errors…
LiveBench is a challenging, contamination-limited LLM benchmark that addresses test set contamination by releasing new questions monthly based on recently-released datasets, arXiv papers, news articles, and IMDb movie synopses.
🧠 Reasoning & Science 4 items
Enhanced version of HumanEval that extends the original test cases by 80x using EvalPlus framework for rigorous evaluation of LLM-synthesized code functional correctness, detecting previously undetected wrong code.
Arena-Hard-Auto is an automatic evaluation benchmark for instruction-tuned LLMs consisting of 500 challenging real-world prompts curated by BenchBuilder. It includes open-ended software engineering problems, mathematical questions, and creative writing tasks.
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
SimpleQA is a factuality benchmark developed by OpenAI that measures the short-form factual accuracy of large language models. The benchmark contains 4,326 short, fact-seeking questions that are adversarially collected and designed to have single, indisputable answers.
Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).
Closest Self-Hostable Open-Weight Alternatives to Phi 4
Open-weight models with full HuggingFace weights for private GPU / Mac deployment
Frequently Asked Questions
Is Phi 4 open-source or proprietary?
Phi 4 (phi-4) is a proprietary commercial model by Microsoft. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.
What are the context limit and API pricing of Phi 4?
Phi 4 supports 16K input context and 14,745 max output tokens, priced at $0.07/1M input ($0.014/1M cached) and $0.14/1M output.