inclusionai
inclusionAI: Ling 3.0 Flash
inclusionai/ling-3.0-flash
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Ling 3.0 Flash is inclusionAI's text-to-text hybrid-linear Mixture-of-Experts model, listed by OpenRouter as inclusionai/ling-3.0-flash with a 262144-token context and reasoning enabled by default. The model card describes 124B total parameters with 5.1B activated per token, a KDA/MLA hybrid design, and training aimed at efficient long-context and agentic workflows. Reported strengths are largely vendor claims; this pack lacks an independent model card beyond OpenRouter and the vendor README, so validate on your workload.[1][2]
Strengths
- Vendor documentation describes a hybrid-linear MoE design using KDA plus MLA, with 124B total and 5.1B active parameters intended to reduce compute per token.[2]
- OpenRouter lists a 262144-token text-to-text context, tool calling and response-format parameters, and reasoning that is enabled by default but not mandatory.[1]
- The model card reports agentic-oriented training across many interactive environments and a caching integration intended to cut repeated computation and TTFT in long-input sessions; treat this as vendor-reported.[2]
Limitations
- Evidence is catalog data plus vendor documentation only; no independent evaluation or readable benchmark tables are included, so workload validation is necessary.[1][2]
- Only text input and output are listed, and the catalog knowledge cutoff is null, so freshness and non-text modalities remain unverified.[1]
- The catalog shows default reasoning with no supported effort levels, and benchmark coverage is sparse, with only Artificial Analysis coding and agentic entries populated.[1]
Where to use it
- Potentially suited to production agentic coding or tool-using assistants where long context and controllable reasoning defaults matter; pilot before adoption.[1][2]
- Candidate for long-document analysis or multi-turn workflows that may benefit from the vendor's reported caching and TTFT optimizations.[1][2]
- May fit self-hosted serving through the vendor-documented SGLang or vLLM recipes when teams need an explicit thinking toggle and OpenAI-style endpoints.[2]
Sources
- [1] OpenRouter catalog · inclusionAI: Ling 3.0 FlashSources checked: Nov 13, 2026
- [2] Model documentation · inclusionAI: Ling 3.0 FlashSources 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* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...
Specifications
- Model ID
- inclusionai/ling-3.0-flash
- Canonical ID
- inclusionai/ling-3.0-flash-20260723
- Creator
- inclusionai
- Added to OpenRouter
- 23.07.2026
- Context length
- 262,144
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.021 / out $0.063
- 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: tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Coding index | 50.6 | BB — next 30% of the cohort | 13.11.2026 |
| Artificial Analysis | Agentic index | 19.3 | 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) |
|---|---|---|---|---|---|---|
| Novita | 262,144 | $0.021 | $0.063 | — | — | 100% |
| DeepInfrafp4 | 131,072 | $0.060 | $0.180 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.