Does O4 Mini support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for O4 Mini is available on request via Opper Enterprise — contact hello@opper.ai.

Where is O4 Mini hosted?

O4 Mini runs on US hosting routes through the Opper gateway.

Is O4 Mini trained on prompts and outputs?

No. Every hosting route for O4 Mini is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for O4 Mini?

Yes. A GDPR Data Processing Agreement is available on at least one route serving O4 Mini. Contact hello@opper.ai to receive it.

O4 Mini

by OpenAI

O4 Mini is OpenAI's compact reasoning model, a generation beyond O3 Mini with strong performance for its size and cost. It excels in mathematics and competitive programming, reaching 99.5 percent pass@1 on AIME 2025 when given access to a Python interpreter, and outperforms O3 Mini across STEM and non-STEM tasks including data science work. The model combines efficient reasoning with practical strengths in coding and visual understanding. It accepts text and image input, with a 200,000 token context window and up to 100,000 output tokens, and supports structured outputs, function calling, and streaming. O4 Mini can use tools within its reasoning, including web search, Python execution, image and file analysis, and image generation. It sustains higher usage limits than larger reasoning models, making it a strong choice for high-throughput applications that need reliable reasoning at lower cost.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

200K

Max output

100K

Input price

$1.10 /1M

Output price

$4.40 /1M

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

Available routes

O4 Mini 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
OpenAI	US	Enterprise	No	$1.10	$4.40

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

Data handling per route

Each route hosting O4 Mini has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

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#134 of 531 LLMs

TierEfficient

Output speed177 tok/s

First token25.87s

Intelligence Index25.6

Coding Index25.6

Math Index90.7

Reasoning & knowledge

MMLU-Pro

83%

GPQA Diamond

78%

Humanity's Last Exam

18%

Long-context reasoning

55%

Coding

LiveCodeBench

86%

SciCode

47%

Agentic & tool use

Terminal-Bench Hard

15%

τ²-Bench Telecom

56%

Math & instruction following

AIME 2025

91%

IFBench

69%

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

Get started

Call O4 Mini 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/o4-mini",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);