When was Ling-3.0-flash-VL released?

InclusionAI released Ling-3.0-flash-VL on 10 Sep 2026. It is available through the Opper gateway.

Does Ling-3.0-flash-VL support zero data retention?

Yes. Ling-3.0-flash-VL is available with zero data retention on DeepInfra through the Opper gateway.

Where is Ling-3.0-flash-VL hosted?

Ling-3.0-flash-VL runs on US hosting routes through the Opper gateway.

Is Ling-3.0-flash-VL trained on prompts and outputs?

No. Every hosting route for Ling-3.0-flash-VL is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Ling-3.0-flash-VL?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Ling-3.0-flash-VL. Contact hello@opper.ai to receive it.

Ling-3.0-flash-VL

by InclusionAI

Released 37 days after Ling 3.0 Flash · All InclusionAI releases

Ling-3.0-flash-VL is the native multimodal member of InclusionAI's Ling-3.0 series, published with MIT-licensed weights in September 2026. It builds on the Ling-3.0-flash Mixture-of-Experts, 124 billion total parameters with 5.5 billion active per token, adding a ViT visual encoder and a two-layer MLP projector in front of a 42-layer hybrid backbone that alternates KDA and gated MLA attention layers at a 5:1 ratio. VideoRoPE encodes spatial position and temporal order so the model can take video as well as images, over a 128K native context that InclusionAI extends to 256K with YaRN scaling. Rather than bolting vision onto a text model, InclusionAI folds visual input into the same understanding, reasoning, planning, acting, and verification process it uses for text, with thinking on by default. That carries into agent use, where the model reads web and software interfaces and turns what it sees into sequences of actions. InclusionAI names visual perception, STEM reasoning, document intelligence, multimodal agents, frontend coding, and medical report interpretation as target areas, and the low active parameter count keeps per-token compute modest relative to the model's total size.

Call Ling-3.0-flash-VL 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

131K

Input price

$0.06 /1M$0.01 cache read

Output price

$0.18 /1M

Released

10 Sep 2026

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

Available routes

Ling-3.0-flash-VL runs on 1 route through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output	Cache read
DeepInfra	US		No	$0.06	$0.18	$0.01

Uptime and availability

Ling-3.0-flash-VL runs on a single route through the Opper gateway today, so its availability is that provider's availability.

100%route uptime, last 30 days

Single route, no failover target within this model.

Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.

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

Data handling per route

Each route hosting Ling-3.0-flash-VL has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

DeepInfra — United States🇺🇸

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

Benchmarks

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

Global rank#162 of 678 LLMs

TierEfficient

Output speed149 tok/s

First token2.15s

Intelligence Index24.6

Coding Index57.0

Reasoning & knowledge

GPQA Diamond

86%

Humanity's Last Exam

22%

Long-context reasoning

78%

Coding

SciCode

44%

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

Get started

Call Ling-3.0-flash-VL through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Ling-3.0-flash-VL 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: "deepinfra/inclusionAI/Ling-3.0-flash-VL",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);