qwenBerbayar
Qwen: Qwen3.5 397B A17B
qwen/qwen3.5-397b-a17b
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...
Harga input / 1M token
$0.5500
Harga output / 1M token
$3.50
Context length
262.144
Modalitas
- Input
- text, image, video
- Output
- text
Parameter yang didukung
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Rilis
16 Februari 2026