← All models
I
inclusionAI: Ling-2.6-flash
inclusionai/ling-2.6-flash
Tool useJSONStreaming
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....
Pricing
Input
$0.01 / 1M
Output
$0.03 / 1M
Specs
Context
262,144 tokens
Input
text
Output
text
Released: 2026-04
Supported parameters
frequency_penaltymax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p