HostYourAI
Get Started
Model garden

Phi 3.5 MoE instruct

Instantly via the EU router or as a dedicated GPU deployment. Data stays in Europe.

Phi-3.5-MoE is a lightweight, state-of-the-art open model built upon datasets used for Phi-3 - synthetic data and filtered publicly available documents - with a focus on very high-quality, reasoning dense data. The model supports multilingual and comes with 128K context length (i...

Start for free ← All models
microsoft/Phi-3.5-MoE-instruct vLLM ready
text->text · microsoft · EU-hosted
42B
Parameters
131K
Context window
97GB
Minimum VRAM
POST /api/v1/chat/completions200 OK

Specifications

Parameters 42B
Context window 131,072 tokens
Minimum VRAM 97 GB
Architecture PhiMoEForCausalLM (vLLM)
License mit
Modality text->text
Released August 2024
Publisher microsoft ↗

Pricing

€0.40
Input (per 1M tokens)
€0.60
Output (per 1M tokens)

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

✓ Verified working on 28-06-2026 — responded in 3148 ms on our EU infrastructure.

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-3.5-MoE-instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Frequently asked questions

Can I run Phi 3.5 MoE instruct in the EU?

Yes. HostYourAI runs Phi 3.5 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 3.5 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 3.5 MoE instruct cost?

Via the shared EU router you pay €0.40 per million input tokens and €0.60 per million output tokens, with no fixed costs. For high volume or isolation you can also run Phi 3.5 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

FastContext 1.0 4B RL

FastContext-1.0 is a lightweight repository-exploration subagent for LLM coding agents. Instead of letting a single model both explore the repository and solve the task, FastContext separates these two roles: it is invoked on demand by a main coding agent, issues parallel read-only tool calls (READ, GLOB, GREP), and returns compact file paths and line ranges as focused context.

4B 262K context View model →
FastContext 1.0 4B SFT

FastContext-1.0 is a lightweight repository-exploration subagent for LLM coding agents. Instead of letting a single model both explore the repository and solve the task, FastContext separates these two roles: it is invoked on demand by a main coding agent, issues parallel read-only tool calls (READ, GLOB, GREP), and returns compact file paths and line ranges as focused context.

4B 262K context 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 →
FrogBoss 32B 2510

FrogBoss is built on the Qwen3-32B transformer architecture with a maximum context length of 64k tokens. The model uses multi-turn debugging workflows and complex code reasoning. Unlike general-purpose LLMs, FrogBoss is specialized for software engineering tasks.

32B 41K 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 →

Try Phi 3.5 MoE instruct for free

Creating an account takes a minute. Test Phi 3.5 MoE instruct straight away in the playground.

Start for free