Kimi K3.1 Pro Highspeed
moonshotai/kimi-k3.1-pro-highspeed
spread (output, p90 ÷ p10)
— too few providers
$20.00 – $30.00 · 3 providers · max÷min 1.5×
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 |
|---|---|---|---|---|
Vercel AI Gateway router / aggregator | $4.00 | $20.00 | $0.20 | $3.36 |
LLM Gateway router / aggregator | $4.00 | $20.00 | $0.20 | $3.36 |
Moonshot AIfirst-party first-party lab | $4.00 | $20.00 | $0.20 | $3.36 |
Requesty router / aggregator | $4.00 | $20.00 | $0.20 | $3.36 |
NanoGPT router / aggregator | $4.00 | $20.00 | $0.20 | $3.36 |
Novita AI inference host | $4.00 | $20.00 | $0.20 | $3.04 |
Venice AI inference host | $6.00 | $30.00 | $0.60 | $4.75 |
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) kimi-k3.1-pro-highspeedsubscription plan
Data: models.dev (MIT), snapshot 2026-10-26. Prices are vendor-published; verify before purchase. Methodology.