Grok 4 Fast Non Reasoning
xai/grok-4-fast-non-reasoning
xAI· 2M ctx
API onlytool call quant: unknown
0 providers priced · 0 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.
No published pricing for this dimension.
| Provider | Input | Output | Cache rd | Blended |
|---|---|---|---|---|
Jiekou.AI reseller | $0.180 | $0.450 | — | $0.205no cache price published |
302.AI reseller | $0.200 | $0.500 | — | $0.227no cache price published |
Abacus router / aggregator | $0.200 | $0.500 | — | $0.227no cache price published |
Helicone router / aggregator | $0.200 | $0.500 | $0.0500 | $0.132 |
Poe router / aggregator | $0.200 | $0.500 | $0.0500 | $0.132 |
Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.