{"schema":"page/1","id":"model:nvidia-nim/deepseek-ai/deepseek-v4.1-flash","kind":"AIModel","title":"deepseek-v4.1-flash","layout":"item","status":"published","summary":"552B MoE, 8B active params with native multimodal support and lower API cost using smaller KV cache","body":[{"type":"model","id":"deepseek-ai/deepseek-v4.1-flash"}],"hero":"","facts":{"via":"NVIDIA","id":"nvidia-nim/deepseek-ai/deepseek-v4.1-flash","model_id":"deepseek-ai/deepseek-v4.1-flash","name":"deepseek-v4.1-flash","description":"552B MoE, 8B active params with native multimodal support and lower API cost using smaller KV cache","family":"deepseek-ai","canonical_slug":null,"price_in":0,"price_out":0,"price_cache_read":null,"price_cache_write":null,"price_cache_write_1h":null,"price_web_search":null,"price_overrides":[],"context":null,"max_completion_tokens":null,"modality":null,"input_modalities":null,"output_modalities":null,"tokenizer":null,"knowledge_cutoff":null,"created":1789757717,"moderated":null,"params":null,"default_parameters":null,"tools":null,"reasoning":null,"reasoning_efforts":null,"reasoning_default_effort":null,"reasoning_mandatory":false,"reasoning_default_enabled":null,"vision":true,"expiration_date":null,"callable":true,"nvidia":{"free_endpoint":true,"partner_endpoint":true,"download":true,"partners":["OpenRouter","Together AI","GMI Cloud","Baseten"],"preview":true,"available":"true","tags":["B200","H100 NVL","CoreWeave","H200 NVL","GB300","Vision Language Model","GB200","Deepinfra","Multimodal MOE","chat","KV Cache Optimization","H200","Causal Encoder Decoder","B300 SXM6 AC","H100 80GB HBM3"]}},"sources":[{"title":"Stored model catalog","url":"https://openrouter.ai/api/v1/models","date":"2026-11-08T09:17:19.329Z"}],"widgets":[],"members":[],"relations":[{"ref":"provider:deepseek-ai","rel":"published by"}],"media":[],"tags":[],"query":{},"created":"2026-11-08T09:17:19.329Z","updated":"2026-11-08T09:17:19.329Z","provenance":{"store":"model-catalog","id":"nvidia-nim/deepseek-ai/deepseek-v4.1-flash","key":"state/models/catalogue.json","original_id":"nvidia-nim/deepseek-ai/deepseek-v4.1-flash","source_kind":"AIModel","source_provider":"NVIDIA","hash":"3a5b986bd594dd339f5d2b32c8064d734cf97ad7a74d86cadb857c7de37fb8dd"},"version":"6bc9b1542673eae422a14b409d91507a85111b1077103879cc95464109687505"}