跳转到主要内容
2026/11/11 12:22 (UTC+8) · New Model · DeepSeek 🚀 DeepSeek V4.1 Flash Economy Edition is live on APIYI at $0.24 input / $0.96 output per 1M tokens The economy edition loads the same V4.1-Flash-1017 weights as the standard deepseek-v4.1-flash, and the vendor states output quality is identical; generation runs slower (roughly 2 s to first token and 15 ms per output token by vendor estimate). APIYI serves it through the BytePlus official channel with full weights — the complete 552B model, no quantization or distillation — and bills one peak-price tier at $0.24 / $0.96, with further savings via recharge bonuses. Both editions and their current status, choose as needed:
  • deepseek-v4-1-flash-economy-261017: Default and SVIP groups, Chat endpoint, $0.24 / $0.96
  • deepseek-v4.1-flash: Default, SVIP, ClaudeCode, and CodexResponses groups, Chat and Anthropic formats, $0.30 / $1.20
For batch work, pass reasoning_effort as none to turn reasoning off; output tokens often drop by an order of magnitude.
← Back to Live Updates · 📚 Monthly archive