Mistral Small 4
mistralai/mistral-small-2603
spread (output, p90 ÷ p10)
— too few providers
$0.600 – $0.930 · 2 providers · max÷min 1.6×
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 |
|---|---|---|---|---|
Kilo Gateway router / aggregator | $0.150 | $0.600 | $0.0150 | $0.105 |
Mistralfirst-party first-party lab | $0.150 | $0.600 | — | $0.191no cache price published |
OpenRouter router / aggregator | $0.150 | $0.600 | $0.0150 | $0.105 |
Opper router / aggregator | $0.150 | $0.600 | — | $0.191no cache price published |
Pioneer unclassified | $0.150 | $0.600 | $0.0150 | $0.117 |
Eden AI router / aggregator | $0.150 | $0.600 | $0.0150 | $0.105 |
EmpirioLabs AI unclassified | $0.150 | $0.600 | $0.150 | $0.191 |
AKI.IO unclassified | $0.200 | $0.600 | — | $0.236no cache price published |
Cortecs router / aggregator | $0.156 | $0.625 | $0.0160 | $0.110 |
Requesty router / aggregator | $0.165 | $0.660 | $0.165 | $0.210 |
Infomaniak inference host | $0.250 | $0.930 | — | $0.312no cache price published |
Stale offerings (not in the spread) · 1
Last priced more than 3 days before the latest snapshot — shown for reference, never mixed into cheapest, median or spread.
- Venice AI mistral-small-2603pay per token
Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.