paza Phi 4 multimodal instruct
Runs as your own dedicated GPU deployment, ready to launch from the wizard. Data stays in Europe.
$ curl https://hostyourai.com/api/v1/audio/transcriptions \
-H "Authorization: Bearer hyai-..." \
-F model="microsoft/paza-Phi-4-multimodal-instruct" \
-F file="@meeting.mp3"
Call it now
Drop-in replacement for OpenAI: change only the base URL and API key. The Anthropic format (/v1/messages) is supported too.
audio->text · microsoft · sovereign EU
Runs on EU infrastructure operated by European companies, from your request to the GPU. See the full chain
Fine-tuning was performed on the entire unified multilingual ASR dataset, comprising the mentioned six languages, to encourage cross-lingual generalization. During fine-tuning, only the audio-specific components: audio embedding module, audio encoder, and audio projection layers,...
- Router
- Router · on request
- Dedicated
- Dedicated · available
Specifications
| Parameters | 5.6B |
|---|---|
| Context window | 131,072 tokens |
| Minimum VRAM | 32 GB |
| Architecture | Phi4MMForCausalLM (vLLM) |
| License | mit |
| Modality | audio->text |
| Released | January 2026 |
| 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.
Frequently asked questions
Can I run paza Phi 4 multimodal instruct in the EU?
Yes. HostYourAI runs paza Phi 4 multimodal 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 paza Phi 4 multimodal 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 paza Phi 4 multimodal instruct cost?
paza Phi 4 multimodal instruct needs several GPUs at once, so it runs as a dedicated deployment billed per GPU minute rather than per token. Tell us your volume and we will work it out with 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 paza Phi 4 multimodal instruct for free
Creating an account takes a minute. Your API key works with paza Phi 4 multimodal instruct right away.







