inclusionAI

Ling 3.1 FlashNEWinclusionAI

inclusionAI built Ling 3.1 Flash for coding, tool use, planning and long-context agent work: a hybrid-reasoning MoE model with about 560B total parameters and roughly 25B active per token, served with a 256K context window.

Ling 3.0 Flash FininclusionAI

Ling 3.0 Flash Fin is inclusionAI's finance-specialised variant of Ling-3.0-flash, keeping the 262K-token context window and adding domain tuning for financial reasoning.

Ling 3.0 Flash SanteinclusionAI

Ling 3.0 Flash Sante is a health-and-medicine model specialized in medical reasoning, evidence-based retrieval, clinical documentation, and medical question answering.

Ling 3.0 Flash VLinclusionAI

Ling 3.0 Flash VL is inclusionAI's vision-language variant of Ling 3.0 Flash: a fast, low-cost multimodal chat model that accepts image, video and text input, with a 131K-token context window, reasoning, streaming, structured output and tool calling.

Ling-3.0-flashinclusionAI

Ling-3.0-flash is inclusionAI's fast, cost-efficient chat model with a 262K-token context window, reasoning, streaming and tool-calling support.