Grok 4.7
xai/grok-4.7
spread (output, p90 ÷ p10)
1.0×
$6.00 – $6.80 · 5 providers · max÷min 1.1×
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 |
|---|---|---|---|---|
Prime Inference unclassified | $1.60 | $4.80 | — | $1.89no cache price published |
Amazon Bedrock hyperscaler | $2.00 | $6.00 | $0.50 | $1.41 |
xAIfirst-partytiered first-party lab | $2.00 | $6.00 | $0.50 | $1.41 |
Requesty router / aggregator | $2.00 | $6.00 | $0.50 | $1.57 |
Tempr Gatewaytiered unclassified | $2.00 | $6.00 | $0.50 | $1.41 |
Vercel AI Gatewaytiered router / aggregator | $2.00 | $6.00 | $0.50 | $1.41 |
302.AI reseller | $2.00 | $6.00 | $0.50 | $1.45 |
Cloudflare AI Gatewaytiered router / aggregator | $2.00 | $6.00 | $0.50 | $1.41 |
CommandCodetiered unclassified | $2.00 | $6.00 | $0.50 | $1.41 |
CrossModeltiered router / aggregator | $2.00 | $6.00 | $0.50 | $1.57 |
Eden AItiered router / aggregator | $2.00 | $6.00 | $0.50 | $1.41 |
Vertextiered hyperscaler | $2.00 | $6.00 | $0.50 | $1.41 |
Kilo Gateway router / aggregator | $2.00 | $6.00 | $0.50 | $1.41 |
LLM Gateway router / aggregator | $2.00 | $6.00 | $0.50 | $1.41 |
Merge Gateway router / aggregator | $2.00 | $6.00 | $0.50 | $1.41 |
NanoGPT router / aggregator | $2.00 | $6.00 | $0.50 | $1.41 |
NEAR AI Cloud inference host | $2.00 | $6.00 | $0.50 | $1.41 |
Ofox reseller | $2.00 | $6.00 | $0.50 | $1.41 |
OpenCodetiered router / aggregator | $2.00 | $6.00 | $0.50 | $1.41 |
OpenCode Gotiered subscription plan | $2.00 | $6.00 | $0.50 | $1.41 |
OpenRoutertiered router / aggregator | $2.00 | $6.00 | $0.50 | $1.41 |
AIHubMixtiered router / aggregator | $2.20 | $6.60 | $0.55 | $1.55 |
Venice AItieredoutlier inference host | $2.27 | $6.80 | $0.57 | $1.60 |
Neon router / aggregator | $2.50 | $7.50 | $0.50 | $1.68 |
Subscription plans (flat fee, not per-token) · 2
Flat-fee plan — the per-token price is bundled into a subscription, so $0/token is not free. Excluded from cheapest, median and spread.
- GitHub Copilot grok-4.7subscription plan
- DevPass (LLM Gateway) grok-4-7subscription plan
Data: models.dev (MIT), snapshot 2026-10-17. Prices are vendor-published; verify before purchase. Methodology.