Phi-4

At a glance

What Phi-4 does

Tool use, Streaming, Structured output, Self-hostable, Small footprint

Best for

Extremely small self-hosted coding model, edge devices, resource-constrained environments

Works well with

Conflicts & caveats

• Trae's built-in model menu may not include Phi-4 — Trae primarily ships with Claude/GPT/Gemini/DeepSeek.
• Google Antigravity is built around Gemini 3 Pro; Claude and recent GPT-5 models also work, but Phi-4 is not in the supported model list.
• Kiro's spec mode is tuned for Claude models — Phi-4 may work but spec-driven flows are best with Claude.
• Cursor's built-in model menu may not include Phi-4 — verify it's available in your Cursor model picker.
• OpenAI Codex (VS Code) is tied to OpenAI's GPT-5.1 Codex family — Phi-4 is not selectable inside this integration.
• Gemini CLI is locked to Google Gemini models — your LLM is Phi-4.
• Privacy conflict: Self-hosted Phi-4 sends code to cloud @codebase (Cursor). Use local context (Continue indexing, ChromaDB, LanceDB, pgvector, Vespa self-hosted) for true privacy.
• Claude Code only works with Claude models — your LLM is Phi-4.
• Devin uses Cognition's proprietary model internally — your selected Phi-4 will be ignored.
• OpenAI Codex (Cloud) runs GPT-5.1 Codex internally — your selected Phi-4 will be ignored.
• Jules runs Gemini models internally — your selected Phi-4 will be ignored.
• The Claude Code SDK is tuned for Claude models — Phi-4 may work via the model adapter but loses Claude-specific features (thinking, prompt caching, sub-agents).
• Lovable uses a fixed internal model — your selected Phi-4 will be ignored.
• Replit Agent 3 uses its own model selection internally — your selected Phi-4 will be ignored.