Does GPT-5 Nano support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for GPT-5 Nano is available on request via Opper Enterprise — contact hello@opper.ai.

Where is GPT-5 Nano hosted?

GPT-5 Nano runs on both EU and US hosting routes through the Opper gateway. Pick the route that matches your residency requirement.

Is GPT-5 Nano trained on prompts and outputs?

No. Every hosting route for GPT-5 Nano is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for GPT-5 Nano?

Yes. A GDPR Data Processing Agreement is available on at least one route serving GPT-5 Nano. Contact hello@opper.ai to receive it.

GPT-5 Nano

by OpenAI

GPT-5 Nano is the fastest and most lightweight version of GPT-5, designed for tasks where speed matters most. With a 272k token context window and support for text and image input, structured output, and tool use, it covers a wide range of practical applications. The model is well suited to summarization, classification, and other simple tasks, serving as the lightest-weight option in OpenAI's GPT-5 lineup. It is a good fit for high-volume applications, responsive subagents, and workloads where latency directly shapes the product experience. Note that GPT-5.4 Nano offers improvements over this variant, with faster latency and stronger reasoning and tool use, making it the recommended choice for new projects.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

272K

Max output

128K

Input price

$0.05 /1M

Output price

$0.40 /1M

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

Available routes

GPT-5 Nano 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	$0.05	$0.40
OpenAI	US	Enterprise	No	$0.05	$0.40

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

Data handling per route

Each route hosting GPT-5 Nano 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#195 of 531 LLMs

TierEfficient

Output speed172 tok/s

First token88.72s

Intelligence Index19.9

Coding Index20.3

Math Index83.7

Reasoning & knowledge

MMLU-Pro

78%

GPQA Diamond

68%

Humanity's Last Exam

Long-context reasoning

42%

Coding

LiveCodeBench

79%

SciCode

37%

Agentic & tool use

Terminal-Bench Hard

12%

τ²-Bench Telecom

37%

Math & instruction following

AIME 2025

84%

IFBench

68%

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

Get started

Call GPT-5 Nano 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-5-nano",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);