# DeepSeek: DeepSeek V4.1 Flash 1017 — price and measured latency by host

Updated October 18, 2026. Served by 11 providers; 5 of them measured here.

Latency and uptime are measured by llmlatency.dev probes. Prices are published by the providers and read via OpenRouter on 2026-10-18 — not measured.

| Host | Input $/M | Output $/M | Context | Fastest p50 | From | Uptime |
| --- | --- | --- | --- | --- | --- | --- |
| deepinfra | $0.078 | $0.235 | 1,048,576 | 161 ms | us-central | 99.9% |
| inference-net | $0.080 | $0.500 | 262,144 | 102 ms | us-central | 100% |
| deepseek | $0.150 | $0.600 | 1,048,576 | 180 ms | ap-tokyo | 100% |
| fireworks | $0.300 | $1.200 | 1,048,576 | 20 ms | ap-tokyo | 99.9% |
| baseten | $0.300 | $1.200 | 1,048,576 | 47 ms | us-central | 100% |

Source: https://llmlatency.dev/model/deepseek-deepseek-v4.1-flash-1017 · CC BY 4.0