Ling-3.0-flash-VL

Released
2026-09-04
Last refreshed
2026-09-08
Status
Researched 45d ago
Open sourceCommercial use: permittedMultimodalRAGAgentsLong contextVisionJSON / Tool useMultimodalAgent
InclusionAI releases · 18 in the last 12 months · this family litChangelog →
Specifications
Family
Ling 3.0
Released
2026-09-04
Context
128K
Parameters
124B (5.5B activated)
Architecture
Mixture of Experts
Specialization
multimodal
Openness
Open source
License
MITOSI-approvedPermitted
Weights
Available
Code
Unknown
Training
Fine-tuned
Created by
InclusionAI

InclusionAI is Ant Group's artificial general intelligence research lab, responsible for developing the Ling series of l

Hangzhou, China
Founded 2023
Website
Pricing
Output / 1M
$0.180
Input / 1M
$0.060

Cheapest of 1 route · OpenRouter · cache read $0.012

Providers(1)
OpenRouter
Links
Website HuggingFace

About

Ling-3.0-flash-VL is InclusionAI's vision-language fine-tune of Ling-3.0-flash (124B total / 5.5B activated MoE) for image and video understanding, reasoning, function calling, and agentic tool use. Native config context is 131,072 tokens; the Hugging Face model card documents YaRN extension up to 1M tokens. MIT-licensed weights on Hugging Face (inclusionAI/Ling-3.0-flash-VL). No first-party USD API pricing published yet.

Providers(1)

Compare API pricing across 1 tracked provider route for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MCacheRoute
OpenRouter$0.060$0.180read $0.012
Serverless

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured Outputs

Benchmark peer barsfor RAG

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

API versions

inclusionAI/Ling-3.0-flash-VL