Kimi K3.1 Pro
moonshotai/kimi-k3.1-pro
spread (output, p90 ÷ p10)
— too few providers
$10.00 – $15.00 · 2 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 |
|---|---|---|---|---|
LLM Gateway router / aggregator | $2.00 | $10.00 | $0.20 | $1.75 |
Merge Gateway router / aggregator | $2.00 | $10.00 | $0.20 | $1.58 |
Moonshot AIfirst-party first-party lab | $2.00 | $10.00 | $0.20 | $1.75 |
Eden AI router / aggregator | $2.00 | $10.00 | $0.20 | $1.58 |
Kilo Gateway router / aggregator | $2.00 | $10.00 | $0.20 | $1.58 |
Requesty router / aggregator | $2.00 | $10.00 | $0.20 | $1.75 |
Vercel AI Gateway router / aggregator | $2.00 | $10.00 | $0.20 | $1.75 |
NanoGPT router / aggregator | $2.00 | $10.00 | $0.20 | $1.75 |
OpenCode Go subscription plan | $2.00 | $10.00 | $0.20 | $1.75 |
OpenRouter router / aggregator | $2.00 | $10.00 | $0.20 | $1.58 |
Prime Inference unclassified | $2.00 | $10.00 | — | $2.73no cache price published |
Venice AI inference host | $3.00 | $15.00 | $0.30 | $2.37 |
Subscription plans (flat fee, not per-token) · 3
Flat-fee plan — the per-token price is bundled into a subscription, so $0/token is not free. Excluded from cheapest, median and spread.
- Kimi For Coding (kimi.com) k3.1-proMainland-China endpointsubscription plan
- Kimi For Coding (kimi.ai) k3.1-prosubscription plan
- DevPass (LLM Gateway) kimi-k3.1-prosubscription plan
Data: models.dev (MIT), snapshot 2026-10-24. Prices are vendor-published; verify before purchase. Methodology.