Does Phi 4 Multimodal support zero data retention?

Yes. Phi 4 Multimodal is available with zero data retention by default on Evroc through the Opper gateway.

Where is Phi 4 Multimodal hosted?

Phi 4 Multimodal runs on EU hosting routes through the Opper gateway, with contractually enforced residency on supported providers.

Is Phi 4 Multimodal trained on prompts and outputs?

No. Every hosting route for Phi 4 Multimodal is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Phi 4 Multimodal?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Phi 4 Multimodal. Contact hello@opper.ai to receive it.

Phi 4 Multimodal

by Microsoft

Phi-4 Multimodal is a lightweight 5.6 billion parameter open-weight foundation model that unifies speech, vision, and text processing in a single architecture using a mixture-of-LoRAs design. It supports a 128K token context window and processes multiple input modalities including text across 23 languages, English visual understanding, and audio in eight languages. Trained on 5 trillion text tokens, 2.3 million speech hours, and 1.1 trillion image-text tokens, the model handles image understanding, optical character recognition, chart and table reasoning, speech recognition and translation, and multi-image analysis. It ranks first on Hugging Face's OpenASR leaderboard and is the first open-source model offering speech summarization. Released under the MIT license in February 2025, Phi-4 Multimodal is designed for memory and compute-constrained environments while maintaining competitive performance on vision benchmarks against larger multimodal models.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

128K

Max output

Input price

$0.11 /1M

Output price

$0.43 /1M

EU residency available
Zero data retention on pay-as-you-go
No training by default
GDPR DPA available

Available routes

Phi 4 Multimodal runs on 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output
Evroc	EU	Zero data retention	No	$0.11	$0.43

Training posture across routes: No training on prompts by default.

Data handling per route

Each route hosting Phi 4 Multimodal has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Evroc — Sweden🇸🇪

Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. EU; DPA available.

Zero data retention: On by default on Pay-as-you-go.
Training: No training on customer data.
Logging: Abuse monitoring
Third-party access: None disclosed
GDPR DPA: DPA available
Transfer mechanism: Not applicable — data stays in EU

Get started

Call Phi 4 Multimodal through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into your coding agent — Claude Code, Cursor, Codex, and more — and it'll wire up Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "evroc/phi-4-multimodal-instruct",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);