Voxtral Small 24B 2507
mistralai/voxtral-small-24b-2507
mistralai· 32K ctx
open weightsstructured quant: unknown
spread (output, p90 ÷ p10)
— too few providers
$0.00230 – $0.513 · 3 providers · max÷min 223×
3 providers priced · 3 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 |
|---|---|---|---|---|
evroc inference host | $0.00230 | $0.00230 | — | $0.00230no cache price published |
Eden AI router / aggregator | $0.100 | $0.300 | — | $0.118no cache price published |
Amazon Bedrock hyperscaler | $0.100 | $0.300 | — | $0.118no cache price published |
Kilo Gateway router / aggregator | $0.100 | $0.300 | $0.0100 | $0.0609 |
OpenRouter router / aggregator | $0.100 | $0.300 | $0.0100 | $0.0609 |
GreenPT inference host | $0.228 | $0.513 | — | $0.254no cache price published |
Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.