Grok 4.20 Multi Agent
xai/grok-4.20-multi-agent
xAI· 128K ctx
API onlytool call quant: unknown
spread (output, p90 ÷ p10)
— too few providers
$2.83 – $2.83 · 1 providers · max÷min 1.0×
1 provider priced · 1 offering
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 |
|---|---|---|---|---|
Vercel AI Gateway router / aggregator | $1.25 | $2.50 | $0.20 | $0.70 |
OpenRoutertiered router / aggregator | $1.25 | $2.50 | $0.20 | $0.70 |
Kilo Gateway router / aggregator | $1.25 | $2.50 | $0.20 | $0.70 |
Venice AItiered inference host | $1.42 | $2.83 | $0.23 | $0.79 |
Poe router / aggregator | $2.00 | $6.00 | $0.20 | $1.22 |
NanoGPT router / aggregator | $2.00 | $6.00 | $1.00 | $1.73 |
Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.