Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
Microsoft

Phi 4

$AffordableRun locally
Microsoft#61 of 92
CompareChat

Microsoft's compact research model with strong STEM reasoning. Small language model excelling at math, coding, and scientific reasoning. Strong performance per parameter ratio for edge deployment.

▼

Phi 4 by Microsoft has a Capability Index of 64.6, making it comparable to the field average. It ranks #61 out of 92 models on the idapt capability leaderboard. Phi 4 is somewhat expensive at $0.07/M tokens input and $0.14/M tokens output. The model supports a 16K context window.

Best forFrontier reasoningCost-effective

Benchmarks

CodingInsufficient data
AgenticInsufficient data
Sources:Epoch ECI·Epoch AI·OpenRouter· as of 2026-07-10

Category Rankings

Capability
#61of 92
Math
#49of 70
Reasoning
#54of 78

Specifications

Vision
Audio
Reasoning
Dense
Architecture
14B
Parameters
16K
Context
16K
Max output
9.1 GB-16 GB
Local download
12 GB-20 GB
Local RAM

Performance

Providers

Run locally

Run Phi 4 on your own computer with the Local AI Engine for free, with no rate limits and no third-party AI provider involved. idapt installs it and routes chat to your hardware automatically.

Download
9.1 GB-16 GB
Recommended RAM
12 GB-20 GB

ollama pull phi4:14b-q4_K_M

Misc

January 10, 2025
Released
CompareChat with Phi 4

Compare with

OpenAIGPT 5.6 Solvs Phi 4OpenAIGPT 5.6 Lunavs Phi 4AnthropicClaude Fable 5vs Phi 4AnthropicClaude Opus 4.8vs Phi 4AnthropicClaude Sonnet 5vs Phi 4AnthropicClaude Haiku 4.5vs Phi 4GoogleGemini 3.6 Flashvs Phi 4GoogleGemini 3.5 Flashvs Phi 4GoogleGemini 3.5 Flash-Litevs Phi 4GoogleGemma 4 31Bvs Phi 4xAIGrok 4.5vs Phi 4xAIGrok Build 0.1vs Phi 4xAIGrok 4.1 Fastvs Phi 4MetaMuse Spark 1.1vs Phi 4DeepSeekDeepSeek V4 Provs Phi 4DeepSeekDeepSeek V4 Flashvs Phi 4MiniMaxMiniMax M3vs Phi 4MoonshotAIKimi K3vs Phi 4MoonshotAIKimi K2.7 Codevs Phi 4Zhipu AIGLM 5.2vs Phi 4QwenQwen3.7 Maxvs Phi 4QwenQwen3.7 Plusvs Phi 4QwenQwen3 Coder Nextvs Phi 4NVIDIANemotron 3 Ultravs Phi 4Mistral AIMistral Small 4vs Phi 4
Frequently Asked Questions about Phi 4▼

When was Phi 4 released?

▼

Phi 4 was released on January 10, 2025.

Who created Phi 4?

▼

Phi 4 was created by Microsoft.

How capable is Phi 4?

▼

Phi 4 has a Capability Index of 64.6/100, making it comparable to the field average. It ranks #61 out of 92 models.

How much does Phi 4 cost?

▼

Phi 4 costs $0.07/M input tokens and $0.14/M output tokens.

What is Phi 4 API pricing?

▼

The Phi 4 API is priced at $0.07 per million input tokens and $0.14 per million output tokens. You can access Phi 4 through idapt.app alongside 200+ other AI models in one workspace.

Is Phi 4 a reasoning model?

▼

No, Phi 4 is not a reasoning model. It responds directly without an extended internal thinking step. For tasks requiring deep chain-of-thought reasoning, consider models like Claude, o-series from OpenAI, or Gemini Thinking.

Does Phi 4 support image or vision input?

▼

No, Phi 4 does not currently support image or vision input. It is a text-only model.

Does Phi 4 support audio?

▼

No, Phi 4 does not support audio input.

What is the context window of Phi 4?

▼

Phi 4 has a context window of 16K tokens, meaning it can process approximately 12,288 words of context at once.

Is Phi 4 open source?

▼

Phi 4 is a proprietary model developed by Microsoft. The model weights and training data are not publicly available.

Where can I use Phi 4?

▼

You can chat with Phi 4 on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access Phi 4 through Microsoft's own API or platform.

  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Credentials
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • idapt Code
  • Code Execution
  • Computers
  • Computer Use
  • Computer Assist · Soon
  • Containers · Soon
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • LLM cost calculator
  • Token counter
  • Context window checker
  • Can I run it
  • Model picker quiz
  • Savings finder
  • Video cost estimator
  • Text to speech cost
  • Transcription cost
  • API endpoint tester
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Skills
  • Learn
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)