DeepSeek R1 0528
deepseek-ai/deepseek-r1-0528
DeepSeek· 164K ctx· mit
open weightstool callreasoning quant: unknown
spread (output, p90 ÷ p10)
1.1×
$2.15 – $5.00 · 4 providers · max÷min 2.3×
4 providers priced · 5 offerings
Cheapest / median / spread use providers that serve the model on their own capacity: first-party lab, hyperscaler, inference host.
Blended $/M assumptions
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.
| Provider | Input | Output | Cache rd | Blended |
|---|---|---|---|---|
NanoGPT router / aggregator | $0.40 | $1.70 | $0.20 | $0.39 |
submodel unclassified | $0.50 | $2.15 | — | $0.65no cache price published |
Meganova unclassified | $0.50 | $2.15 | — | $0.65no cache price published |
OpenRouter router / aggregator | $0.50 | $2.15 | $0.35 | $0.55 |
Deep Infra inference host | $0.50 | $2.15 | $0.35 | $0.55 |
Alibaba (China)CN first-party lab | $0.50 | $2.18 | — | $0.65no cache price published |
Kilo Gateway router / aggregator | $0.70 | $2.50 | $0.35 | $0.64 |
Jiekou.AI reseller | $0.70 | $2.50 | — | $0.86no cache price published |
NovitaAI inference host | $0.70 | $2.50 | $0.35 | $0.64 |
Cortecs router / aggregator | $0.65 | $2.57 | $0.16 | $0.52 |
TensorX unclassified | $0.66 | $2.60 | $0.17 | $0.59 |
Hugging Face inference host | $3.00 | $5.00 | — | $3.18no cache price published |
Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.