ERNIE-4.5 VL 424B A47B
baidu/ernie-4.5-vl-424b-a47b
spread (output, p90 ÷ p10)
— too few providers
$1.25 – $1.25 · 1 providers · max÷min 1.0×
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.
| Provider | Input | Output | Cache rd | Blended |
|---|---|---|---|---|
Jiekou.AI reseller | $0.42 | $1.25 | — | $0.50no cache price published |
Kilo Gateway router / aggregator | $0.42 | $1.25 | — | $0.50no cache price published |
LLM Gateway router / aggregator | $0.42 | $1.25 | — | $0.50no cache price published |
NovitaAI inference host | $0.42 | $1.25 | — | $0.50no cache price published |
OpenRouter router / aggregator | $0.42 | $1.25 | — | $0.50no cache price published |
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) ernie-4.5-vl-424b-a47bsubscription plan
Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.