Model dossier

inclusionAI: Ling-2.6-flash

Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-world agents that require fast responses, strong execution, and high token efficiency....

ProviderinclusionAI Start comparison

Context262,144

Max output32,768

Pricing viewTVP price

Identity

inclusionAI: Ling-2.6-flash

Model ID: inclusionai/ling-2.6-flash
Canonical slug: inclusionai/ling-2.6-flash-20260421
Knowledge cutoff: n/a
Created: 4/21/2026

Capabilities

texttoolsstructured

Modalities

text->texttext

Capacity

Context262,144

Max output32,768

TokenizerOther