Back to all models
inclusionai

inclusionAI: Ling 3.1 Flash

Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.

inclusionai/ling-3.1-flash

Context Size

1,000K

Input Price

9,000 pts/M554 Ks/M

Output Price

27,000 pts/M1,660 Ks/M


Architecture

Text

Supported Parameters

frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningrepetition_penaltyseedstoptemperaturetool_choicetoolstop_ktop_logprobstop_p

Details

TokenizerOther
Max Completion262,144 tokens
Provider Context1,000K tokens
ModeratedNo
CreatedOct 2, 2026