Ling 3.0 Flash VL is the vision-language member of inclusionAI's Ling 3.0 Flash family. It keeps the speed and low cost of the text-only Flash models while accepting image, video and text input, returning text output.
It ships with a 131,072-token context window and up to 32,768 output tokens, and supports reasoning, streaming responses, structured output and tool/function calling.
Read charts, tables, UI screenshots and scanned pages, and return structured output that downstream code can consume directly.
Accepts video input alongside text, making it suitable for clip-level description, tagging and summarisation tasks.
At $0.082524 per 1M input tokens it is priced for batch classification, captioning and moderation workloads where per-request cost dominates.
Function calling plus vision lets the model inspect an image and then call an external tool with structured arguments in the same turn.
Released September 10, 2026.
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Visual document analysis: the model is documented as handling object counting, complex layouts, charts, and document content, making it suited to reading and analyzing visual documents.
Visual reasoning and verification: it is documented for calculation, multi-step reasoning, and external information verification using visual evidence.
Web and software interface automation: it is documented as able to understand web and software interfaces and translate that visual information into sequences of actions.
Video understanding tasks: it is documented as supporting video understanding, including event localization, long-video question answering, and video clip editing.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "inclusionai/ling-3.0-flash-vl", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "inclusionai/ling-3.0-flash-vl", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"inclusionai/ling-3.0-flash-vl","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| Intelligence | 24.6 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 22, 2026 |
| Coding | 57 | Composite score across standardised coding evaluations, measured independently by Artificial Analysis | Source | September 22, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Ling 3.0 Flash VL This page | Low-cost image and video understanding | |||
| Fast, low-cost reasoning and tool use at scale | ||||
| Finance-domain reasoning over long documents | ||||
| High-volume, zero-cost chat and reasoning tasks | ||||
| Reasoning + agents |
Ling 3.0 Flash VL is the vision-language member of inclusionAI's Ling 3.0 Flash line: a fast, low-cost chat model that accepts image, video and text input and returns text.
It keeps the Flash line's speed-oriented design and adds visual understanding. Ling 3.0 Flash takes text only; the VL variant also accepts images and video.
inclusionAI, the AI research group at Ant Group.
It takes image, video and text input and returns text.
131,072 tokens, with up to 32,768 tokens of output.
Yes, it supports function calling and structured outputs, alongside streaming responses and reasoning.
High-volume multimodal work where per-request cost matters: document and screenshot understanding, image and video captioning, tagging and moderation pipelines.
Yes. The model also answers to the alias ling-3.0-flash-vl.
Send a request to the chat completions endpoint with the model id inclusionai/ling-3.0-flash-vl. The request shape is the same as for any other chat model on AI/ML API.
