Phi 3 medium 4k instruct
Runs as your own dedicated GPU deployment, ready to launch from the wizard. Data stays in Europe.
$ curl https://hostyourai.com/api/v1/chat/completions \
-H "Authorization: Bearer hyai-..." \
-H "Content-Type: application/json" \
-d '{
"model": "microsoft/Phi-3-medium-4k-instruct",
"messages": [{"role": "user", "content": "Hello!"}]
}'
Call it now
Drop-in replacement for OpenAI: change only the base URL and API key. The Anthropic format (/v1/messages) is supported too.
text->text · microsoft · sovereign EU
Runs on EU infrastructure operated by European companies, from your request to the GPU. See the full chain
Phi 3 medium 4k instruct is an open-source language model from Microsoft with 14B parameters and a 4K-token context window, hosted on EU GPUs via an OpenAI-compatible API.
- Router
- Router · on request
- Dedicated
- Dedicated · available
Specifications
| Parameters | 14B |
|---|---|
| Context window | 4,096 tokens |
| Minimum VRAM | 48 GB |
| Architecture | Phi3ForCausalLM (vLLM) |
| License | mit |
| Modality | text->text |
| Released | May 2024 |
| Publisher | microsoft ↗ |
Pricing
Shared router · per token
Dedicated GPU · per hour
Shared EU router, you pay only per token. Dedicated GPU deployments are billed per minute, see pricing.
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.
Translated from its LiveBench result onto the same scale.
Range 26.3 to 40.6
Sources: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Refreshed daily, last on 19-11-2026
LiveBench · 29.3
LiveBench · All tasks
| web of lies v2 | 40.0 |
|---|---|
| zebra puzzle | 30.0 |
| spatial | 40.0 |
| LCB generation | 26.9 |
|---|---|
| coding completion | 14.0 |
| AMPS Hard | 28.0 |
|---|---|
| math comp | 15.6 |
| olympiad | 15.2 |
| cta | 54.0 |
|---|---|
| tablejoin | 4.9 |
| tablereformat | 36.0 |
| connections | 14.0 |
|---|---|
| plot unscrambling | 15.7 |
| typos | 12.0 |
| paraphrase | 56.5 |
|---|---|
| simplify | 55.8 |
| story generation | 52.6 |
| summarize | 48.4 |
Frequently asked questions
Can I run Phi 3 medium 4k instruct in the EU?
Yes. HostYourAI runs Phi 3 medium 4k 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 medium 4k 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 medium 4k instruct cost?
Phi 3 medium 4k instruct is available on request: through the shared EU router after a quick chat, or as your own dedicated GPU deployment billed per minute. 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
One platform, four layers
Start with one layer and add the others when the work asks for it. They share one key, one balance and one Activity view.
Try Phi 3 medium 4k instruct for free
Creating an account takes a minute. Test Phi 3 medium 4k instruct straight away in the playground.







