
DeepSeek-V4.1-Flash-1017 是深度求索(DeepSeek)于 2026年10月17日 发布的轻量级/高性能 AI 模型版本,百万 token 上下文,全新非对称架构,推理吞吐更高、KV 缓存成本大幅降低,综合 Agent、推理性能优于 V4-Pro,API 支持 OpenAI/Anthropic 双协议。
| Providers | Credit report | Credit | Region | Formats | Price | TTFT | Throughput | 7-day success rate | 7-day calls | Availability (24h) | Status | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| - | Guangzhou | Input: ¥0.8/ 1M tokensOutput: ¥3.2/ 1M tokens | 3189 ms | 78 tokens/s | 99.15% | 117 | In service | |||||
| View report | 4.5 | Guangzhou | Input: ¥0.8/ 1M tokensOutput: ¥3.2/ 1M tokens | 1800 ms | 12 tokens/s | 100% | 28 | In service | ||||
| View report | 4.5 | Guangzhou | Input: ¥0.84/ 1M tokensOutput: ¥3.36/ 1M tokens | 4526 ms | 60 tokens/s | 97.37% | 21K | In service | ||||
| - | Guangzhou | Input: ¥0.9/ 1M tokensOutput: ¥3.6/ 1M tokens | - | 5 tokens/s | 100% | 12 | In service | |||||
| View report | 4.5 | Guangzhou | Input: ¥1/ 1M tokensOutput: ¥4/ 1M tokens | 1829 ms | 115 tokens/s | 96.63% | 11.2K | In service | ||||
| - | Guangzhou | Input: ¥1.2/ 1M tokensOutput: ¥4.8/ 1M tokens | 2079 ms | 112 tokens/s | 97.58% | 1.26M | In service |
No more