deepseek-v4.1POST
QuickSilver Pro hosts V4.1 Flash 1017 at DeepSeek's own pricing
The third-party platform says it offers the Oct 17 snapshot at $0.15 input / $0.60 output per 1M tokens with $0.003 cached input, 1M context, image input, tool calls and zero data retention.
QuickSilver Pro
@qspro_aiArchived 11 days agoOriginally posted 2026.10.17
QuickSilver Pro @qspro_aiOriginally posted 2026.10.17
DeepSeek V4.1 Flash 1017 is live on QuickSilver Pro, day one. The Oct 17 snapshot of V4.1 Flash, at DeepSeek's own price: • $0.15 in / $0.60 out per 1M tokens • cached input $0.003 • 1M context, text + image input • reasoning on/off, tool calls, strict JSON schema • zero data retention One OpenAI-compatible API: model="deepseek-v4.1-flash-1017" https://quicksilverpro.io/models/deepseek-v4.1-flash-1017/
This post quotes another post: x.com/deepseek_ai/status/2111375640717033777
x.com/qspro_ai/status/2111479539809636678Archived 2026.10.18 16:43