Ling 3.1 Flash 1019

InclusionAI's updated Ling reasoning model targets complex analysis and multi-step tasks using application-supplied tools. Its hybrid-linear mixture-of-experts architecture activates 25 billion of 560 billion parameters, with further post-training beyond the original Ling 3.1 Flash.

CONTEXT1M

MAX OUTPUT256K

LAST SCAN03 Nov 2026

🏆First observed free at Kilo on 31 Oct 2026.

Reasoning Open weights Text

Free aggregator routes

These are the aggregator routes recorded in the current or last published catalog. Each route keeps its exact model ID and thinking information.

Limits above: Kilo. Available gateway routes are listed below.

The supplied Kilo catalog snapshot identifies inclusionai/ling-3.1-flash-1019-free, matching the exact dated version in InclusionAI's creator repository https://huggingface.co/inclusionAI/Ling-3.1-flash-1019. The creator explicitly describes 1019 as an upgraded version of Ling-3.1-flash. It therefore remains separate from the supplied known undated Ling 3.1 Flash routes; no pinned serving precision or repository revision is established.

Kilo

Info

Thinking: Supported

Model ID · Kilo APIinclusionai/ling-3.1-flash-1019-free

Model sources

Use it through LiteLLM

Import the current LiteLLM-compatible YAML and use the exact model ID shown above. The catalog is generated from the same reviewed scan data as the download.

Download LiteLLM YAML