DeepSeek V4.1 Flash 1017
deepseek-ai/deepseek-v4.1-flash-1017
Cheapest / median / spread use providers that serve the model on their own capacity: first-party lab, hyperscaler, inference host.
blended = 90.9% input × [(1 − 70% cache) × input + 70% cache × cache-read] + 9.1% × output + cache writes (30% of uncached input) where a write price is published
A provider that publishes no cache price is blended with cache share 0 (all input at the input price) and labelled “no cache price published” — never penalised against identical in/out prices.
No published pricing for this dimension.
| Provider | Input | Output | Cache rd | Blended |
|---|---|---|---|---|
Vercel AI Gateway router / aggregator | $0.150 | $0.600 | $0.00300 | $0.0974 |
LLM Gateway router / aggregator | $0.150 | $0.600 | $0.00300 | $0.0974 |
OpenRouter router / aggregator | $0.150 | $0.600 | $0.00300 | $0.0974 |
Kilo Gateway router / aggregator | $0.150 | $0.600 | $0.00300 | $0.0974 |
NanoGPT router / aggregator | $0.150 | $0.600 | $0.00300 | $0.0974 |
Requesty router / aggregator | $0.50 | $1.50 | $0.05 | $0.30 |
Subscription plans (flat fee, not per-token) · 1
Flat-fee plan — the per-token price is bundled into a subscription, so $0/token is not free. Excluded from cheapest, median and spread.
- DevPass (LLM Gateway) deepseek-v4.1-flash-1017subscription plan
Data: models.dev (MIT), snapshot 2026-10-17. Prices are vendor-published; verify before purchase. Methodology.