Phi 4
Open weightMicrosoft · Released January 2025 · Knowledge cutoff June 2024
[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...
Facts and pricing
- Provider
- Microsoft
- Context window
- 16K tokens
- Input price
- 0.77 credits / 1M tokens ($0.070 raw)
- Output price
- 1.5 credits / 1M tokens ($0.14 raw)
- Vision (image input)
- No
- Tool calling
- No
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.
Try Phi 4 now
What Phi 4 is best for
- Everyday chat and drafting on an open-weight model with transparent lineage
Microsoft family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| Phi 4 | 16K | 0.77 | 1.5 | January 2025 |
| WizardLM-2 8x22B | 66K | 6.8 | 6.8 | April 2024 |
Frequently asked questions
- What is Phi 4?
- Phi 4 is an AI model by Microsoft. [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...
- How much does Phi 4 cost on Zeplik?
- Input tokens cost 0.77 credits per million and output tokens 1.5 credits per million (1 credit = $0.10; the raw provider rates are $0.070 and $0.14 per million). New accounts start with free credits.
- How long can a conversation with Phi 4 be?
- Phi 4 has a 16K-token context window (16,384 tokens), which covers the conversation plus any documents you attach.
- Does Phi 4 support images and tools?
- Phi 4 is text-only and does not support tool calling.
Related models
WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is...
GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...
GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode
Ling 3.0 Flash Sante is a health and medicine-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for...
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
More you can do with Phi 4
- 465 AI skillsReady-to-run expert methods for writing, data, code and more, each running on Phi 4 or any model you pick.
- 997 integrationsConnect Gmail, Slack, GitHub, Notion and hundreds more so the assistant can work in your apps.
- Simple pricingPlus, Pro and Max plans with a monthly credit allowance that works across every model.