Does Cosmos3-Super-Reasoner support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for Cosmos3-Super-Reasoner is available on request via Opper Enterprise — contact hello@opper.ai.

Where is Cosmos3-Super-Reasoner hosted?

Cosmos3-Super-Reasoner runs on EU hosting routes through the Opper gateway, with contractually enforced residency on supported providers.

Is Cosmos3-Super-Reasoner trained on prompts and outputs?

No. Every hosting route for Cosmos3-Super-Reasoner is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Cosmos3-Super-Reasoner?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Cosmos3-Super-Reasoner. Contact hello@opper.ai to receive it.

Cosmos3-Super-Reasoner

by NVIDIA

Cosmos3-Super-Reasoner is a fully open 64B-parameter omnimodel (a 32B reasoner paired with a 32B generator) built to advance physical AI research through native multimodal reasoning and generation. It is designed for large-scale synthetic data generation and policy model development, natively understanding and generating text, images, video, ambient sound, and actions in unified workflows. The model targets robotics, autonomous systems, and vision AI agents, combining world generation, physical reasoning, and action generation in a single model rather than stitching together several specialized ones. NVIDIA positions it as one of the first fully open omnimodels of its kind for physical AI. With a 262K token context, it handles long-horizon reasoning scenarios and is suited to researchers and engineers building foundation models for physical systems, training robotic policies from synthetic data, and developing agentic AI for embodied task planning.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

262K

Max output

—

Input price

$0.10 /1M

Output price

$0.30 /1M

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

Available routes

Cosmos3-Super-Reasoner 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
Nebius	EU	Enterprise	No	$0.10	$0.30

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

Data handling per route

Each route hosting Cosmos3-Super-Reasoner has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Nebius — Finland🇫🇮

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
Third-party access: None disclosed
GDPR DPA: DPA available
Transfer mechanism: Not applicable — data stays in EU

Get started

Call Cosmos3-Super-Reasoner 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: "nebius/nvidia/Cosmos3-Super-Reasoner",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);