# Phi > Phi, a family of models by Microsoft, listed from OpenRouter. Indexed, not reviewed: facts and our own checks, no score or ranking. Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with… - Canonical: https://www.anchorterminal.com/tools/microsoft-phi - Markdown: https://www.anchorterminal.com/tools/microsoft-phi.md (~450 tokens) - Slim: https://www.anchorterminal.com/tools/microsoft-phi.min.md (~380 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/microsoft-phi.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - Updated: 2026-10-04 # Phi > Indexed, not reviewed: facts from OpenRouter and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/ - Kind: model family, by Microsoft - Category: Model APIs & inference (https://www.anchorterminal.com/categories/inference.md) - Listed because: OpenRouter lists it, with prices from the providers that serve it. - What OpenRouter says: \[Microsoft Research\](/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... ## Models (1) | Model | OpenRouter id | Released | Context | Input $/1M | Output $/1M | Supports | | --- | --- | --- | --- | --- | --- | --- | | Phi 4 | `microsoft/phi-4` | 2025-01 | 16k | $0.07 | $0.14 | structured output | Prices and limits as OpenRouter lists them; a provider's own price can differ. - JSON: https://www.anchorterminal.com/api/v1/tools/microsoft-phi.json - Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming