Phi 4 by OpenRouter | AI model information

Loading models

Subscribe

Follow catalog updates and new guides

Open RSS feed Medium guides

RSS covers catalog changes. Medium covers how-to guides and write-ups.

Phi 4 by OpenRouter | AI model information

$10 off Synthetic - fastest OpenCode provider$10 off Synthetic - the fastest Kimi K2.6 and GLM 5.1 provider Discuss

Model details

Phi 4

Loading model overview

OpenRoutermicrosoft/phi-4phi

Open provider page Provider docs

Quick Info

Provider: OpenRouter
Model key: microsoft/phi-4
Release date: Jan 10, 2025
Last updated: Jan 10, 2025

Cost

Input token cost: $0.065
Output token cost: $0.14

Limits

Output tokens: 16,384 tokens
Context window

Latest news about Phi 4

Videos about Phi 4

Recent tweets and retweets from OpenRouter

More models around Phi 4

Also served by

This exact model name is also listed by 3 other providers.

Azure Azure Cognitive Services GitHub Models

3 providers

Phi 4 Mini Instruct

Currently listed through these providers:

OpenRouter GitHub Models Weights & Biases

3 providers

Currently listed through these providers:

Azure Azure Cognitive Services Nvidia

3 providers

Phi-4-mini-reasoning

Currently listed through these providers:

Azure Azure Cognitive Services GitHub Models

3 providers

Phi-4-reasoning

Currently listed through these providers:

Azure Azure Cognitive Services GitHub Models

3 providers

Phi-3.5-mini instruct (128k)

Currently listed through these providers:

Azure Azure Cognitive Services GitHub Models

3 providers

Phi-3.5-MoE instruct (128k)

Currently listed through these providers:

Azure Azure Cognitive Services GitHub Models

3 providers

Phi-3-medium instruct (128k)

Currently listed through these providers:

Azure Azure Cognitive Services GitHub Models

3 providers

Phi-3-mini instruct (128k)

Currently listed through these providers:

Azure Azure Cognitive Services GitHub Models

3 providers

Phi-3-small instruct (128k)

Currently listed through these providers:

Azure Azure Cognitive Services GitHub Models

2 providers

Phi-4-multimodal

Currently listed through these providers:

Azure Azure Cognitive Services

2 providers

Phi-4-reasoning-plus

Currently listed through these providers:

Azure Azure Cognitive Services

1 provider

Currently listed through:

Discuss this model

Powered byHyvor Talk

Add corrections, implementation notes, pricing changes, or usage caveats for other readers.

Knowledge cutoff

2024-06-30

Input modalities

Output modalities

Capabilities

16,384 tokens

Recent tweets and retweets from OpenRouter

May 19, 2026, 10:55 PMUTC

05.19.2026 GMI Cloud hits ~90B tokens of DeepSeek V4 in one day on @OpenRouter , ~290B in one week. Thank you to everyone who built with us 🙌

May 19, 2026, 6:34 PMUTC

Read more about the model: nitter.net/GoogleDeepMind/status/…

May 19, 2026, 6:34 PMUTC

Try it now: openrouter.ai/google/gemini-…

May 19, 2026, 6:34 PMUTC

Gemini 3.5 Flash from @GoogleDeepMind is live on OpenRouter! Beats Gemini 3.1 Pro on coding, agentic work, and tool use at Flash-tier price and speed. 1M context, 65K max output, multimodal. $1.50/M input, $9/M output.

May 19, 2026, 3:33 PMUTC

Parallel Search is now in @OpenRouter. Use Parallel for configurable context size, domain filtering, and clean, structured results that deliver the best accuracy and token efficiency.