Does GPT-4o support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for GPT-4o is available on request via Opper Enterprise — contact hello@opper.ai.

Where is GPT-4o hosted?

GPT-4o runs on both EU and US hosting routes through the Opper gateway. Pick the route that matches your residency requirement.

Is GPT-4o trained on prompts and outputs?

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

Is a GDPR DPA available for GPT-4o?

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

GPT-4o

by OpenAI

GPT-4o is OpenAI's omnimodal model, able to reason across text, vision, and audio. It performs strongly on reasoning, coding, math, and instruction following while retaining broad general knowledge, and it processes visual input natively. It supports structured output that conforms to a JSON schema and function calling for tool integration. The 128,000 token context window handles long documents, code reviews, and multi-turn agentic workflows. It is a solid default for production applications that need strong general capability, reliable behaviour, and multimodal understanding.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

128K

Max output

16K

Input price

$2.50 /1M

Output price

$10.00 /1M

EU residency available
US residency available
Zero data retention via Enterprise
No training by default
GDPR DPA available

Available routes

GPT-4o runs on 2 different routes 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
Azure	EU	Enterprise	No	$2.75	$11.00
OpenAI	US	Enterprise	No	$2.50	$10.00

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

Data handling per route

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

Azure — Sweden🇸🇪

Zero data retention is available via Opper Enterprise contract. No training on customer data. EU; DPA available.

Zero data retention: Available via Opper Enterprise contract.
Training: No training on customer data.
Logging: Abuse monitoring (30-day retention)
Third-party access: None disclosed
GDPR DPA: DPA available
Transfer mechanism: Not applicable — data stays in EU

OpenAI — United States🇺🇸

Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.

Zero data retention: Available via Opper Enterprise contract.
Training: No training on customer data.
Logging: Abuse monitoring (30-day retention)
Third-party access: None disclosed
GDPR DPA: DPA available
Transfer mechanism: SCCs

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#302 of 531 LLMs

TierEfficient

Output speed165 tok/s

First token0.49s

Intelligence Index11.2

Coding Index16.7

Math Index6.0

Reasoning & knowledge

MMLU-Pro

75%

GPQA Diamond

54%

Humanity's Last Exam

Long-context reasoning

Coding

LiveCodeBench

31%

SciCode

33%

Agentic & tool use

Terminal-Bench Hard

τ²-Bench Telecom

25%

Math & instruction following

AIME 2025

IFBench

34%

See full leaderboard →Benchmarks via Artificial Analysis · View on AA

Get started

Call GPT-4o 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: "openai/gpt-4o",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);