Phi-4 Reasoning: context, capabilities and where to run it
Prices from official vendor price lists · October 2026
Microsoft does not publish a token price for Phi-4 Reasoning, so cost depends on where it is hosted. Recorded here for reasoning, open weights.
Capabilities
Context window
32.8K tokens
Price / mo
API only
Phi-4 Reasoning is an AI model from Microsoft. The vendor does not publish a public per-token price, so the cost cells are left empty rather than guessed.
It holds 32.8K tokens in a single conversation. Capabilities recorded in this rating: text & chat, reasoning, tool calling, multilingual, open weights. Access is through the API rather than a consumer subscription.
API priceNot publishedper 1M tokens, in / out
Context32.8K tokenstokens per conversation
VendorMicrosoftall models from this vendor
TierUnpricedno public rate card
Compared with alternatives
How Phi-4 Reasoning sits against its neighbours in this rating. Tap a card to open that model.
Good and poor fit
Good fit
- Multi-step analysis, planning and code review, where the first plausible answer is often wrong.
- General text generation and conversation across languages.
Poor fit
- Anything requiring image input — this model does not accept it.
- Work where the vendor does not publish a rate you can budget against.
Related filters
Text & chat234 models for text generation and chat
Reasoning175 models that think before answering
Tool calling172 models that call your functions
MultilingualAll 245 models work beyond English
Open weights94 models you can download and self-host
Microsoft3 models from this vendor
All 245 modelsThe full rating with filters and prices
Frequently asked questions
How much does Phi-4 Reasoning cost?
Microsoft does not publish a public per-token rate for this model, so the price cells here are empty rather than estimated.
What is the context window of Phi-4 Reasoning?
32.8K tokens in a single conversation.
What can Phi-4 Reasoning do?
In this rating it is recorded with: text & chat, reasoning, tool calling, multilingual, open weights.
Is Phi-4 Reasoning a good choice?
It depends on the job. See the good-fit and poor-fit lists above, and compare against the neighbouring models before committing.
Frequently searched
By capabilityReasoningCodingVisionLong context 1M+Free tierOpen weightsLow latencyRealtime voiceImage generation
By vendorAnthropic (13)OpenAI (30)Google DeepMind (17)xAI (8)Meta (6)DeepSeek (9)Mistral AI (11)Alibaba (Qwen) (40)Z.ai (12)Moonshot AI (5)
Ratings 0
Avg. score 0
Rate this page
Help us improve