Using Phi-1.5 on Microsoft Foundry
Implementation guide · Phi-1 · Microsoft Research
Quick Start
- 1
- 2Use the Microsoft Foundry SDK or REST API to call
phi-1.5— see the documentation for request format. - 3You'll be billed $0.07/1M input, $0.07/1M output tokens.
About Microsoft Foundry
Microsoft Foundry offers a comprehensive platform-as-a-service for enterprise AI operations. It provides multiple deployment options including Serverless APIs (pay-as-you-go), Global Standard (shared managed capacity), Provisioned Throughput Units (reserved capacity), batch processing, and bring-your-own model deployments. The platform features a unified control plane for models, agents, tools, and observability. Its Agent Service enables building and deploying AI agents with built-in tracing, monitoring, and governance. Evaluation and monitoring tools assess model performance, safety, and groundedness. Foundry supports seamless upgrades from Azure OpenAI with non-destructive migration, maintaining existing deployments while unlocking multi-provider model access and advanced platform capabilities.
Microsoft Foundry is a unified enterprise AI platform that significantly expands beyond Azure OpenAI. It functions as a multi-provider hosting and deployment platform for LLMs, supporting models from OpenAI, Anthropic, DeepSeek, xAI, Meta, Mistral, NVIDIA, and others. Foundry integrates agent services, evaluation, observability, and governance into a single Azure control plane. Key capabilities include a multi-provider model catalog, Model Router for intelligent prompt routing, Foundry Agent Service for building and deploying AI agents with built-in tracing and monitoring, and enterprise-grade governance with RBAC, compliance, and regional deployments. For broader model catalog including Claude, DeepSeek, Grok, Llama, Mistral, and NVIDIA Nemotron, Foundry is the recommended platform over Azure OpenAI.
Pricing on Microsoft Foundry
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.07 |
| Output tokens | $0.07 |
Capabilities
About Phi-1.5
Phi-1.5 is a 1.3-billion parameter large language model (LLM) developed by Microsoft, designed to excel in complex reasoning tasks, particularly those requiring common sense, language understanding, and logical reasoning. Unlike many LLMs that heavily depend on web-scraped data, Phi-1.5 primarily uses a high-quality, synthetic dataset comprising about 30 billion tokens. This dataset is curated to resemble "textbook-like" content, concentrating on common sense and general knowledge, and sets the model apart. The Phi-1.5 architecture is a standard Transformer with 24 layers, 32 heads, and a head dimension of 64. It incorporates rotary embeddings and flash-attention for efficiency, utilizing a codegen-mono tokenizer. This model demonstrates impressive performance on various natural language benchmarks, rivaling models five times its size, with notable strengths in multi-step reasoning tasks, such as math word problems and coding challenges. However, Phi-1.5's capabilities are not without limitations, as it may produce inaccurate code or facts and is sensitive to prompt variations. The model's training leverages several data sources, with variations like Phi-1.5-web-only and Phi-1.5-web, providing insights into the impact of different datasets on performance.