When was Carina 60B released?

Multiverse Computing released Carina 60B on 15 Jul 2026. It is available through the Opper gateway.

Does Carina 60B support zero data retention?

Yes. Carina 60B is available with zero data retention on Multiverse Computing through the Opper gateway.

Where is Carina 60B hosted?

Carina 60B runs on both EU and US hosting routes through the Opper gateway. Pick the route that matches your residency requirement.

Is Carina 60B trained on prompts and outputs?

No. Every hosting route for Carina 60B is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Carina 60B?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Carina 60B. Contact hello@opper.ai to receive it.

Carina 60B

by Multiverse Computing

Announcement · All Multiverse Computing releases

Carina 60B is a 60-billion-parameter model from Multiverse Computing, built on the gpt-oss architecture and compressed with the company's CompactifAI method. It replaces Multiverse's earlier HyperNova 60B. It always reasons, with low, medium and high effort, and supports tool calling and structured output over a 131K-token context. It suits agents, extraction and other high-volume text work where cost matters more than peak capability.

Call Carina 60B on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Get your API key Try in chat Compare

Key info

Input

Output

Features

Context window

131K

Max output

—

Input price

$0.02 /1M

Output price

$0.09 /1M

Released

15 Jul 2026

Web search

Via Opper

EU residency available
US residency available
Zero data retention on pay-as-you-go
No training by default
GDPR DPA available

Available routes

Carina 60B runs on 2 different routes through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below. In the EU it is served by Multiverse Computing (Spain). See every model hosted in the EU.

Provider	Region	Zero data retention	Training	Input	Output	Cache read
Multiverse Computing	EU		No	$0.02	$0.09	Input price
Multiverse Computing	US		No	$0.02	$0.09	Input price

Live routes and prices as JSON: api.opper.ai/v3/models?q=carina-60b

Data handling per route

Each route hosting Carina 60B has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Multiverse Computing — Spain🇪🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU; DPA available.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: No classifier
Caching: Content cached for replay
GDPR DPA: DPA available
Transfer mechanism: Not applicable — data stays in EU

Multiverse Computing — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs; DPA available.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: No classifier
Caching: Content cached for replay
GDPR DPA: DPA available
Transfer mechanism: SCCs

Get started

Call Carina 60B through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Carina 60B is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

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 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: "carina-60b",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);