Ling-2.6-flash
inclusionAI · 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....
texttext->text
Context
Max context: 262144
Max output: 32768
Max output: 32768
Pricing
Input / 1M: 0.01
Output / 1M: 0.03
Blend / 1M: 0.02
Output / 1M: 0.03
Blend / 1M: 0.02
Quality
Quality index: —
Provider
Provider: inclusionAI
Moderated: no
Moderated: no