HostYourAI
Product
EU RouterHostYourAI CodeOpenAI-compatible APIAnthropic-compatible APIModel GardenDedicated InstancesPlaygroundFine-tuning (Loes)Connect your GPU pool
Solutions
Use cases
HostYourAI CodeLLM InferenceRAG pipelinesChatbotsAI agentsFine-tuning
Industries
GovernmentHealthcareFinanceLegal
Models
DeepSeek V4 ProDeepSeek V4 FlashGLM 5.2Llama 3.1 405BQwen3.5 397BLlama 3.3 70BMistralDeepSeek R1All models →
Compare
Azure OpenAIAWS BedrockClaude APIChatGPTOpenAI
Resources
DocumentationGuide: migrate to the EU RouterGuide: deploy your own LLM (vLLM)Guide: build RAG on EU GPUsModel catalog
Pricing
NL EN DE
Login Book Demo Get Started
Model garden Router · on request Dedicated · on request

Phi mini MoE instruct

This model runs as a dedicated deployment on large GPUs and isn't in the shared playground by default. Get in touch and we'll set it up for you.

Phi-mini-MoE is a lightweight Mixture of Experts (MoE) model with 7.6B total parameters and 2.4B activated parameters. It is compressed and distilled from the base model shared by Phi-3.5-MoE and GRIN-MoE using the SlimMoE approach, then post-trained via supervised fine-tuning an...

Request access ← All models
microsoft/Phi-mini-MoE-instruct On request
text->text · microsoft · EU-hosted
7.6B
Parameters
4K
Context window
24GB
Minimum VRAM
POST /api/v1/chat/completions On request

Specifications

Parameters 7.6B
Context window 4,096 tokens
Minimum VRAM 24 GB
Architecture PhiMoEForCausalLM (vLLM)
License mit
Modality text->text
Released June 2025
Publisher microsoft ↗

Pricing

Shared router · per token
On request
Not available on the shared router. Pricing on request as a dedicated GPU deployment.
Dedicated GPU · per hour
On request
Dedicated deployment, from 24 GB of VRAM. Billed per GPU-hour.

Shared EU router, pay-per-token, scale-to-zero. Dedicated GPU deployments are billed hourly, see pricing.

Call it now

Drop-in replacement for OpenAI: change only the base URL and API key. The Anthropic format (/v1/messages) is supported too.

curl https://hostyourai.com/api/v1/chat/completions \
  -H "Authorization: Bearer hyai-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "microsoft/Phi-mini-MoE-instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Frequently asked questions

Can I run Phi mini MoE instruct in the EU?

Yes. HostYourAI runs Phi mini MoE instruct on GPUs in European datacenters via vLLM. Prompts and outputs never leave the EU and there is no US cloud provider in the chain.

Is hosting Phi mini MoE instruct GDPR-compliant?

Yes. All processing happens inside the EU, a Data Processing Agreement (DPA) is available and the subprocessor list is public. Open-source weights also mean: no training on your data.

How much does Phi mini MoE instruct cost?

Via the shared EU router you pay €0.05 per million input tokens and €0.12 per million output tokens, with no fixed costs. For high volume or isolation you can also run Phi mini MoE instruct as a dedicated hourly GPU instance.

Is the API OpenAI-compatible?

Yes. You use the standard OpenAI SDKs with a custom base URL (https://hostyourai.com/api/v1). The Anthropic Messages API is supported as a drop-in as well.

More models from Microsoft

GELab Zero 4B preview Sico Evolution

GELab Zero 4B preview Sico Evolution is an multimodal language model from Microsoft with 4.4B parameters, hosted on EU GPUs via an OpenAI-compatible API.

4.4B View model →
X Reasoner 7B

We introduce X-Reasoner, a vision-language model posttrained solely on general-domain text for generalizable reasoning, using a twostage approach: an initial supervised fine-tuning phase with distilled long chainof-thoughts, followed by reinforcement learning with verifiable rewards. Experiments show that X-Reasoner successfully transfers reasoning capabilities to both multimodal and out-of-domain settings, outperforming existing state-of-theart models trained with in-domain and multimodal data across various general and medical benchmarks. More details can be found in the paper: X-Reasoner: T

8.3B 128K context View model →
OptiMind SFT

OptiMind-SFT is a specialized 20B parameter model designed to bridge the gap between natural language and executable optimization solvers. It automates the translation of complex decision-making problems—such as supply chain planning, scheduling, and resource allocation—into correct MILP formulations.

21B 131K context View model →
Fara 7B

Description: Fara-7B is Microsoft's first agentic small language model (SLM) designed specifically for computer use. With only 7 billion parameters, Fara-7B is an ultra-compact Computer Use Agent (CUA) that achieves state-of-the-art performance within its size class and is competitive with larger, more resource-intensive agentic systems.

8.3B 128K context View model →
UserLM 8b

Unlike typical LLMs that are trained to play the role of the "assistant" in conversation, we trained UserLM-8b to simulate the “user” role in conversation (by training it to predict user turns in a large corpus of conversations called WildChat). This model is useful in simulating more realistic conversations, which is in turn useful in the development of more robust assistants.

8B 8K context View model →
MediPhi Instruct

The MediPhi Model Collection comprises 7 small language models of 3.8B parameters from the base model Phi-3.5-mini-instruct specialized in the medical and clinical domains. The collection is designed in a modular fashion. Five MediPhi experts are fine-tuned on various medical corpora (i.e. PubMed commercial, Medical Wikipedia, Medical Guidelines, Medical Coding, and open-source clinical documents) and merged back with the SLERP method in their base model to conserve general abilities. One model combined all five experts into one general expert with the multi-model merging method BreadCrumbs. F

3.8B 131K context View model →

Request access

Phi mini MoE instruct isn't available by default yet. Leave your details and we'll arrange a dedicated deployment.

Request access