inclusionai
inclusionAI: Ling 3.0 Flash VL
inclusionai/ling-3.0-flash-vl
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
inclusionai/ling-3.0-flash-vl is presented by the OpenRouter catalog and InclusionAI documentation as a multimodal MoE model accepting text, images, and video and returning text. The sources describe 124B total parameters with 5.5B active per token, visual encoders and temporal video positioning, reasoning on by default, tool and structured-output support, and agent-oriented visual workflows. Catalog context is 131,072 tokens, while the model card describes a 256K configuration requiring a specific YaRN serving recipe. Reported evaluations indicate multimodal, coding, and agentic capability, but evidence remains largely catalog and vendor documentation.[1][2]
Strengths
- Source-reported multimodal input coverage: text, image, and video are accepted, with text output.[1][2]
- Sparse activation: model documentation describes 124B total parameters and 5.5B active per token for inference efficiency.[2]
- Agent-oriented interface: reasoning is enabled by default and the API exposes tools and structured outputs.[1][2]
Limitations
- Evidence is limited to an aggregator catalog and vendor documentation, so independent verification is absent.[1][2]
- Context differs by source and deployment: OpenRouter lists 131,072 tokens, while the model card's 256K claim relies on a YaRN serving configuration.[1][2]
- Benchmark evidence is reported rather than task-specific validation; suitability should be tested on the intended workload.[1][2]
Where to use it
- Worth evaluating for document, chart, and interface understanding where visual evidence matters.[2]
- Candidate for long-video question answering, event localization, or clip-oriented workflows.[2]
- Candidate for multimodal agent prototypes that combine visual observations with tool calls or structured outputs.[1][2]
Sources
- [1] OpenRouter catalog · inclusionAI: Ling 3.0 Flash VLSources checked: Nov 13, 2026
- [2] Model documentation · inclusionAI: Ling 3.0 Flash VLSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...
Specifications
- Model ID
- inclusionai/ling-3.0-flash-vl
- Canonical ID
- inclusionai/ling-3.0-flash-vl-20260910
- Creator
- inclusionai
- Added to OpenRouter
- 10.09.2026
- Context length
- 131,072
- Modality
- text+image+video->text
- Input modalities
- text, image, video
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.060 / out $0.180
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Coding | BB — next 30% of the cohort | — |
| Agents | BB — next 30% of the cohort | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | input: video |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Coding index | 57 | BB — next 30% of the cohort | 13.11.2026 |
| Artificial Analysis | Agentic index | 28.7 | BB — next 30% of the cohort | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| DeepInfrafp4 | 131,072 | $0.060 | $0.180 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.