Does Llama 4 Maverick 17B 128E Instruct FP8 support zero data retention?

Yes. Llama 4 Maverick 17B 128E Instruct FP8 is available with zero data retention by default on DeepInfra, Novita through the qynio gateway.

Where is Llama 4 Maverick 17B 128E Instruct FP8 hosted?

Llama 4 Maverick 17B 128E Instruct FP8 runs on US hosting routes through the qynio gateway.

Is Llama 4 Maverick 17B 128E Instruct FP8 trained on prompts and outputs?

No. Every hosting route for Llama 4 Maverick 17B 128E Instruct FP8 is configured so customer prompts and outputs are not used to train models by default.

Is a no-KYC deposit available for Llama 4 Maverick 17B 128E Instruct FP8?

Yes. A no-KYC Data Processing Agreement is available on at least one route serving Llama 4 Maverick 17B 128E Instruct FP8. Contact hello@qyn.io to receive it.

Llama 4 Maverick 17B 128E Instruct FP8

by Meta

Llama 4 Maverick is a natively multimodal mixture-of-experts model with 17 billion active parameters across 128 experts and 400 billion total parameters. Released in April 2025, it features a 1-million-token context window, letting it handle long documents and reasoning tasks that combine text with visual content. The model uses an early-fusion architecture to integrate text and image tokens natively, supporting multi-image inputs alongside text prompts. It was trained on roughly 22 trillion tokens of multimodal data with an August 2024 knowledge cutoff, and Meta positions it for visual recognition, image reasoning, captioning, and visual question answering. It is offered in both BF16 and FP8 formats and runs on a single H100 host or distributed setups. Meta reports that Maverick beats GPT-4o and Gemini 2.0 Flash across a broad range of widely reported benchmarks, making it well suited to applications that need strong image understanding and reasoning over visual information at scale.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

Max output

Input price

$0.20 /1M

Output price

$0.80 /1M

US residency available
Zero data retention on pay-as-you-go
No training by default
no-KYC deposit available

Available routes

Llama 4 Maverick 17B 128E Instruct FP8 runs on 3 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
DeepInfra	US	Zero data retention	No	$0.20	$0.80
DigitalOcean	US	Not by default	No	$0.20	$0.70
Novita	US	Zero data retention	No	$0.27	$0.85

Uptime and availability

Llama 4 Maverick 17B 128E Instruct FP8 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 100% over the same window.

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

2 monitored providers serve Llama 4 Maverick 17B 128E Instruct FP8.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 1 further route for this model is not on the board yet and is not counted above. See uptime for every provider qynio monitors.

Data handling per route

Each route hosting Llama 4 Maverick 17B 128E Instruct FP8 has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio with a last-verification timestamp.

DeepInfra — United States🇺🇸

Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; unknown; deposit available.

Zero data retention: On by default on Pay-as-you-go. Derived from the logging and moderation facts.
Training: No training on customer data.
Logging: None
Moderation: Not established
Caching: Not established
Subprocessor access: Not established
no-KYC deposit: deposit available
Transfer mechanism: unknown

DigitalOcean — United States🇺🇸

Zero data retention is not on by default — a moderation hold applies. No training on customer data. US; dpf sccs; deposit available.

Zero data retention: Not by default — a moderation hold applies. Derived from the logging and moderation facts.
Training: No training on customer data.
Logging: None
Moderation: Holds content for review
Caching: Content cached for replay
Subprocessor access: No subprocessor reads content
no-KYC deposit: deposit available
Transfer mechanism: dpf sccs

Novita — United States🇺🇸

Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; wallets; deposit available.

Zero data retention: On by default on Pay-as-you-go. Derived from the logging and moderation facts.
Training: No training on customer data.
Logging: None
Moderation: Not established
Caching: Not established
Subprocessor access: Not established
no-KYC deposit: deposit available
Transfer mechanism: wallets

Get started

Call Llama 4 Maverick 17B 128E Instruct FP8 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: "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);