Ministral 14B
mistralai/ministral-14b
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 |
|---|---|---|---|---|
LLM Gateway router / aggregator | $0.200 | $0.200 | — | $0.200no cache price published |
NanoGPT router / aggregator | $0.200 | $0.200 | $0.100 | $0.136 |
Pioneer unclassified | $0.200 | $0.200 | $0.200 | $0.216 |
Vercel AI Gateway router / aggregator | $0.200 | $0.200 | $0.0200 | $0.0855 |
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) ministral-14b-2512subscription plan
Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.