--- title: Microsoft: Phi 4 API | Text Generation | ModelsLab description: Build with Microsoft: Phi 4 API by Microsoft. Text generation, chat, code, and reasoning. Pay-per-use. Free tier. url: https://modelslab.com/models/microsoft/microsoft-phi-4/api.md canonical: https://modelslab.com/models/microsoft/microsoft-phi-4/api.md type: product component: Playground/LLM/Index generated_at: 2026-04-15T04:00:28.969461Z --- Microsoft: Phi 4 --- [LLMs.txt](https://modelslab.com/models/open_router/microsoft-phi-4/llms.txt) [.md](https://modelslab.com/models/microsoft/microsoft-phi-4.md) microsoft-phi-4 microsoft Closed Source Model $0.102500 / call Microsoft: Phi 4 --- Choose a prompt below to get started or type your own message Explain quantum computing in simple terms Write a Python function to sort a list Create a marketing email for a SaaS product Compare REST vs GraphQL APIs Send ### Microsoft: Phi 4 microsoft microsoft-phi-4 Copy model ID PricingInput $0.065 / 1M tokens Output $0.14 / 1M tokens API EndpointsOpenAI Compatible `https://modelslab.com/api/v7/llm/chat/completions`Endpoint Anthropic Compatible `https://modelslab.com/api/v7/llm/v1/messages`Messages `https://modelslab.com/api/v7/llm/v1/messages/count_tokens`Count Tokens `https://modelslab.com/api/v7/llm/v1/models`Models Use with Claude Code cURL Example ParametersSystem MessageYou are a helpful AI assistant specialized in providing accurate and detailed responses. Temperature0.7 Max Tokens1000 Top P0.9 Frequency Penalty0 Presence Penalty0 Model Info Support Related Models --- Discover similar models you might be interested in [View all LLM Models](https://modelslab.com/models?feature=llmaster) [NH](https://modelslab.com/models/open_router/nousresearch-hermes-2-pro-llama-3-8b)[Open Router](https://modelslab.com/models/open_router) [NousResearch: Hermes 2 Pro - Llama-3 8B Closed Source Model](https://modelslab.com/models/open_router/nousresearch-hermes-2-pro-llama-3-8b) [QQ](https://modelslab.com/models/open_router/qwen-qwen3-30b-a3b)[Open Router](https://modelslab.com/models/open_router) [Qwen: Qwen3 30B A3B Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen3-30b-a3b) [Q7](https://modelslab.com/models/together_ai/Qwen-Qwen2.5-7B-Instruct-Turbo)[Together AI](https://modelslab.com/models/together_ai) [Qwen2.5 7B Instruct Turbo Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen2.5-7B-Instruct-Turbo) [AC](https://modelslab.com/models/open_router/anthropic-claude-3.5-haiku)[Open Router](https://modelslab.com/models/open_router) [Anthropic: Claude 3.5 Haiku Closed Source Model](https://modelslab.com/models/open_router/anthropic-claude-3.5-haiku) [AN](https://modelslab.com/models/open_router/amazon-nova-micro-v1)[Open Router](https://modelslab.com/models/open_router) [Amazon: Nova Micro 1.0 Closed Source Model](https://modelslab.com/models/open_router/amazon-nova-micro-v1) [GG](https://modelslab.com/models/open_router/google-gemini-3.1-pro-preview-customtools)[Open Router](https://modelslab.com/models/open_router) [Google: Gemini 3.1 Pro Preview Custom Tools Closed Source Model](https://modelslab.com/models/open_router/google-gemini-3.1-pro-preview-customtools) [QQ](https://modelslab.com/models/open_router/qwen-qwq-32b)[Open Router](https://modelslab.com/models/open_router) [Qwen: QwQ 32B Closed Source Model](https://modelslab.com/models/open_router/qwen-qwq-32b) [CV](https://modelslab.com/models/together_ai/deepcogito-cogito-v2-1-671b)[Together AI](https://modelslab.com/models/together_ai) [Cogito v2.1 671B Closed Source Model](https://modelslab.com/models/together_ai/deepcogito-cogito-v2-1-671b) [QQ](https://modelslab.com/models/open_router/qwen-qwen3-235b-a22b-2507)[Open Router](https://modelslab.com/models/open_router) [Qwen: Qwen3 235B A22B Instruct 2507 Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen3-235b-a22b-2507) [NN](https://modelslab.com/models/open_router/nvidia-nemotron-3-nano-30b-a3b)[Open Router](https://modelslab.com/models/open_router) [NVIDIA: Nemotron 3 Nano 30B A3B Closed Source Model](https://modelslab.com/models/open_router/nvidia-nemotron-3-nano-30b-a3b) [GG](https://modelslab.com/models/open_router/google-gemma-3-12b-it-free)[Open Router](https://modelslab.com/models/open_router) [Google: Gemma 3 12B (free) Closed Source Model](https://modelslab.com/models/open_router/google-gemma-3-12b-it-free) [OG](https://modelslab.com/models/open_router/openai-gpt-5.1)[Open Router](https://modelslab.com/models/open_router) [OpenAI: GPT-5.1 Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-5.1) [QQ](https://modelslab.com/models/open_router/qwen-qwen2.5-vl-32b-instruct)[Open Router](https://modelslab.com/models/open_router) [Qwen: Qwen2.5 VL 32B Instruct Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen2.5-vl-32b-instruct) [AA](https://modelslab.com/models/arcee_ai/arcee_ai-arcee-spotlight)[ModelsLab](https://modelslab.com/models/arcee_ai) [Arcee AI Spotlight Closed Source Model](https://modelslab.com/models/arcee_ai/arcee_ai-arcee-spotlight) [L3](https://modelslab.com/models/meta/nvidia-Llama-3.1-Nemotron-70B-Instruct-HF)[ModelsLab](https://modelslab.com/models/meta) [Llama 3.1 Nemotron 70B Instruct HF Closed Source Model](https://modelslab.com/models/meta/nvidia-Llama-3.1-Nemotron-70B-Instruct-HF) [OG](https://modelslab.com/models/open_router/openai-gpt-4.1-nano)[Open Router](https://modelslab.com/models/open_router) [OpenAI: GPT-4.1 Nano Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-4.1-nano) [QQ](https://modelslab.com/models/open_router/qwen-qwen3-coder-plus)[Open Router](https://modelslab.com/models/open_router) [Qwen: Qwen3 Coder Plus Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen3-coder-plus) [AC](https://modelslab.com/models/open_router/anthropic-claude-opus-4.1)[Open Router](https://modelslab.com/models/open_router) [Anthropic: Claude Opus 4.1 Closed Source Model](https://modelslab.com/models/open_router/anthropic-claude-opus-4.1) About Microsoft: Phi 4 --- \[Microsoft Research\](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion... ### Technical Specifications Model IDmicrosoft-phi-4CategoryLLM ModelsTaskText GenerationPrice$0.102500 per million tokensAddedFebruary 20, 2026 ### Key Features - Chat completion and multi-turn conversation API - Streaming response with token-by-token output - Function calling and tool use support - System prompts and role-based messaging - JSON mode and structured output ### Quick Start Integrate Microsoft: Phi 4 into your application with a single API call. Get your API key from the [pricing page](https://modelslab.com/pricing) to get started. PythonJavaScriptcURLPHP ``` import requests import json url = "https://modelslab.com/api/v7/llm/chat/completions" headers = { "Content-Type": "application/json" } data = { "model_id": "microsoft-phi-4", "messages": [ { "role": "user", "content": "Hello!" } ], "max_tokens": 1000, "key": "YOUR_API_KEY" } try: response = requests.post(url, headers=headers, json=data) response.raise_for_status() # Raises an HTTPError for bad responses (4XX or 5XX) result = response.json() print("API Response:") print(json.dumps(result, indent=2)) except requests.exceptions.HTTPError as http_err: print(f"HTTP error occurred: {http_err} - {response.text}") except Exception as err: print(f"Other error occurred: {err}") ``` View the [full API documentation](https://modelslab.com/models/microsoft/microsoft-phi-4/api) for SDKs, code examples in Python, JavaScript, and more. ### Pricing Microsoft: Phi 4 API costs $0.102500 per million tokens. Pay only for what you use with no minimum commitments. [View pricing plans](https://modelslab.com/pricing) ### Use Cases - AI chatbots and virtual assistants - Code generation and developer tools - Content writing and copywriting automation - Data analysis, summarization, and extraction [Browse LLM Models](https://modelslab.com/models?feature=llmaster) [More from Microsoft](https://modelslab.com/models/open_router) [View Pricing](https://modelslab.com/pricing) Microsoft: Phi 4 FAQ --- ### What is Microsoft: Phi 4? \[Microsoft Research\](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion... ### How do I use the Microsoft: Phi 4 API? You can integrate Microsoft: Phi 4 into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "microsoft-phi-4" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation. ### How much does Microsoft: Phi 4 cost? Microsoft: Phi 4 costs $0.102500 per million tokens. ModelsLab uses pay-per-use pricing with no minimum commitments. A free tier is available to get started. ### What is the Microsoft: Phi 4 model ID? The model ID for Microsoft: Phi 4 is "microsoft-phi-4". Use this ID in your API requests to specify this model. ### Does Microsoft: Phi 4 have a free tier? Yes, ModelsLab offers a free tier that lets you try Microsoft: Phi 4 and other AI models. Sign up to get free API credits and start building immediately. --- *This markdown version is optimized for AI agents and LLMs.* **Links:** - [Website](https://modelslab.com) - [API Documentation](https://docs.modelslab.com) - [Blog](https://modelslab.com/blog) --- *Generated by ModelsLab - 2026-04-15*