When was GPT-5.3 Codex released?

OpenAI released GPT-5.3 Codex on 5 Feb 2026. It is available through the qynio gateway.

Does GPT-5.3 Codex support zero data retention?

Not by default. See the per-route data-handling section for each route's logging stance and retention window.

Where is GPT-5.3 Codex hosted?

GPT-5.3 Codex runs on both EU and US hosting routes through the qynio gateway. Pick the route that matches your residency requirement.

Is GPT-5.3 Codex trained on prompts and outputs?

No. Every hosting route for GPT-5.3 Codex is configured so customer prompts and outputs are not used to train models by default.

Is a no-KYC deposit available for GPT-5.3 Codex?

Yes. A no-KYC Data Processing Agreement is available on at least one route serving GPT-5.3 Codex. Contact hello@qyn.io to receive it.

GPT-5.3 Codex

by OpenAI

Released 56 days after GPT-5.2 · All OpenAI releases

GPT-5.3 Codex is OpenAI's most advanced agentic coding model, trained with reinforcement learning on real-world software engineering tasks. It reaches state-of-the-art performance on SWE-Bench Pro and far exceeds prior results on Terminal-Bench 2.0, both rigorous evaluations of production software engineering, while using fewer output tokens than any prior OpenAI model. The model pairs frontier coding performance with general reasoning to support long-horizon technical work across the software lifecycle, including debugging, deployment, monitoring, documentation, tests, and metrics. It reliably completes complex tasks such as large refactors, code migrations, and feature implementations without losing context. With a 272k token context window, GPT-5.3 Codex excels at writing, reading, and modifying code across large projects. It supports structured output and tool use for integration with development workflows and automation systems.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

272K

Max output

128K

Input price

$1.75 /1M

Output price

$14.00 /1M

Released

5 Feb 2026

onchain settlement available
US residency available
No training by default
no-KYC deposit available

Available routes

GPT-5.3 Codex runs on 2 different routes through the qynio gateway. Compare residency, zero retention, and training posture at a glance — full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output
Azure	EU	Not by default	No	$1.75	$14.00
OpenAI	US	Not by default	No	$1.75	$14.00

Uptime and availability

GPT-5.3 Codex runs on 2 independently monitored routes through the qynio gateway. A direct integration leaves you on one of them, the gateway serves whichever is healthy.

100%effective uptime, last 30 days

Averaged across these routes on their own, a single provider reached 98.03% over the same window.

Daily status through the gateway, which serves each request from whichever route is healthy.

2 monitored providers serve GPT-5.3 Codex.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider qynio monitors.

Data handling per route

Each route hosting GPT-5.3 Codex has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio with a last-verification timestamp.

Azure — Sweden🇸🇪

Zero data retention is not on by default — abuse monitoring, 30-day retention. No training on customer data. EU; deposit available.

Zero data retention: Not by default — abuse monitoring, 30-day retention. Derived from the logging and moderation facts.
Training: No training on customer data.
Logging: Abuse monitoring (30-day retention)
Moderation: Not established
Caching: Not established
Subprocessor access: Not established
no-KYC deposit: deposit available
Transfer mechanism: Not applicable — data stays in EU

OpenAI — United States🇺🇸

Zero data retention is not on by default — abuse monitoring, 30-day retention. No training on customer data. US; wallets; deposit available.

Zero data retention: Not by default — abuse monitoring, 30-day retention. Derived from the logging and moderation facts.
Training: No training on customer data.
Logging: Abuse monitoring (30-day retention)
Moderation: Not established
Caching: Not established
Subprocessor access: Not established
no-KYC deposit: deposit available
Transfer mechanism: wallets

Benchmarks

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

Global rank#73 of 630 LLMs

TierStrong

Output speed126 tok/s

First token43.10s

Intelligence Index45.5

Reasoning & knowledge

GPQA Diamond

92%

Humanity's Last Exam

43%

Long-context reasoning

78%

Coding

SciCode

53%

Agentic & tool use

Terminal-Bench Hard

53%

τ²-Bench Telecom

86%

Math & instruction following

IFBench

75%

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

Get started

Call GPT-5.3 Codex through the qynio gateway with one API key. Let your coding agent set it up, or call it directly — qynio is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up qynio for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.QYN_API_KEY,
5  baseURL: "https://api.qyn.io/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "openai/gpt-5.3-codex",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);