Skip to main content

Microsoft models

Microsoft Research publishes the Phi models, small releases trained on carefully curated data that compete with much larger ones on reasoning. Zeplik carries Phi 4 and the WizardLM-2 8x22B mixture-of-experts model.

Ask a Microsoft model now

Ask Phi 4 anything. Your prompt opens in the Zeplik app with this model selected.

Phi 4

All 1 Microsoft model

Pricing at a glance

ModelContextInput cr/MOutput cr/MReleased
Phi 416K0.841.7January 2025

Frequently asked questions

Which Microsoft models can I use on Zeplik?
Zeplik carries 1 Microsoft model: Phi 4. They all run in the same chat, so you do not need a separate Microsoft account or API key.
How much do Microsoft models cost on Zeplik?
Output tokens cost 1.7 credits per million (raw provider rate $0.14 per million). 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin.
Which Microsoft model has the largest context window?
Phi 4, at 16K tokens (16,384). The context window covers the conversation plus any documents you attach.
Do Microsoft models support images and tool calling?
None of the 1 accept image input, and none support tool calling.
Do I need a paid plan to use Microsoft models on Zeplik?
All 1 need a paid plan (Plus or above). Usage is then billed in credits from your monthly allowance.
What is the newest Microsoft model on Zeplik?
Phi 4, released January 2025. [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.

Other providers

Explore Zeplik