HostYourAI
Product
EU RouterDecision models like JevHostYourAI CodeOpenAI-compatible APIAnthropic-compatible APIModel GardenDedicated InstancesPlaygroundFine-tuning (Loes)Earn with your GPU
Solutions
Use cases
HostYourAI CodeLLM InferenceRAG pipelinesChatbotsAI agentsFine-tuning
Industries
GovernmentHealthcareFinanceLegal
Models
Kimi K3DeepSeek V4 ProDeepSeek V4 FlashGLM 5.3Kimi K2.7 CodeQwen3.5 397BLlama 3.3 70BMistralMiniMax M3All models →
Compare
Azure OpenAIAWS BedrockClaude APIChatGPTOpenAICompare costs
Resources
DocumentationSavings checkGuide: migrate to the EU RouterGuide: deploy your own LLM (vLLM)Guide: build RAG on EU GPUsModel catalogNewsSecurityFAQ
Pricing News
NL EN DE FR ES
Login Book Demo Get Started
Model garden Router · on request Dedicated · available

Phi tiny MoE instruct

Runs as your own dedicated GPU deployment, ready to launch from the wizard. Data stays in Europe.

Phi-tiny-MoE is a lightweight Mixture of Experts (MoE) model with 3.8B total parameters and 1.1B 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...

Start for free ← All models
microsoft/Phi-tiny-MoE-instruct vLLM ready
text->text · microsoft · sovereign EU
Runs on EU infrastructure operated by European companies; US marketplace capacity is never part of this chain. Full chain
3.8B
Parameters
4K
Context window
16GB
Minimum VRAM
POST /api/v1/chat/completions On request

Specifications

Parameters 3.8B
Context window 4,096 tokens
Minimum VRAM 16 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
from €1,08 per hour
Your own vLLM instance on European cloud (16 GB VRAM), billed hourly.

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

✓ Verified working on 30-07-2026, responded in 2566 ms on our EU infrastructure.

Bench index

Bench is our quality index for every model, 0 to 100. It rests on public measurements (Epoch AI with about 40 benchmarks, LiveBench, LMArena and more) and is refreshed every morning. Where nobody measures, it shows an estimate with a range.

~33.2 / 100 · Estimate

No public benchmark yet: estimated from size and release date.

Range 21.6 to 44.8

Sources: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Refreshed daily, last on 23-10-2026

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-tiny-MoE-instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Frequently asked questions

Can I run Phi tiny MoE instruct in the EU?

Yes. HostYourAI runs Phi tiny 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 tiny 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 tiny MoE instruct cost?

Phi tiny MoE instruct is available on request: through the shared EU router after a quick chat, or as your own dedicated GPU deployment billed per hour. Tell us your use case and we will set it up for you.

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

UserRepGen 4B

UserRepGen-4B is a fine-tuned Qwen3.5-4B language model that generates a structured, natural-language user representation from a multi-turn user-assistant conversation. Each representation contains a task description and a behavior description for a user, and is intended to condition a separate LLM-based user simulator.

4.5B 262K context View model →
AesCode 32B

AesCode generates information-rich visual artifacts such as slides, posters, and dashboards as HTML/CSS. The output remains structured, editable, and verifiable, but the task poses a distinct challenge: code models cannot see how layout, hierarchy, and color come together on the canvas.

33B 262K context View model →
AesCode 8B

AesCode generates information-rich visual artifacts such as slides, posters, and dashboards as HTML/CSS. The output remains structured, editable, and verifiable, but the task poses a distinct challenge: code models cannot see how layout, hierarchy, and color come together on the canvas.

8.8B 262K context View model →
Fara1.5 27B

Fara1.5-27B is a multimodal computer use agent (CUA) for web browsers, from Microsoft Research AI Frontiers. It observes the browser through screenshots and acts on the user's behalf by emitting structured tool calls — click, type, scroll, visit URL, web search, and so on — to complete tasks end-to-end.

27B 262K context View model →
Fara1.5 4B

Fara1.5-4B is a multimodal computer use agent (CUA) for web browsers, from Microsoft Research AI Frontiers. It observes the browser through screenshots and acts on the user's behalf by emitting structured tool calls — click, type, scroll, visit URL, web search, and so on — to complete tasks end-to-end.

4.5B 262K context View model →
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 →

Try Phi tiny MoE instruct for free

Creating an account takes a minute. Test Phi tiny MoE instruct straight away in the playground.

Start for free