Back to all models
inclusionai
inclusionaiinclusionAI: 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....
inclusionai/ling-2.6-flash
Context Size
262.144K
Input Price
1,000 Ks/M
Output Price
3,000 Ks/M
Architecture
Text
Supported Parameters
frequency_penaltymax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Details
TokenizerOther
Max Completion32,768 tokens
Provider Context262.144K tokens
ModeratedNo
CreatedApr 21, 2026