Grok 4 Fast
xai/grok-4-fast
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 |
|---|---|---|---|---|
ZenMux router / aggregator | $0.200 | $0.500 | $0.0500 | $0.132 |
Helicone router / aggregator | $3.00 | $15.00 | $0.75 | $2.66 |
FastRouter router / aggregator | $3.00 | $15.00 | $0.75 | $3.89 |
Poe router / aggregator | $3.00 | $15.00 | $0.75 | $2.66 |
LLM Gateway router / aggregator | $3.00 | $15.00 | $0.75 | $2.66 |
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) grok-4subscription plan
Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.