LongCat-2.0
meituan-longcat/longcat-2.0
spread (output, p90 ÷ p10)
— too few providers
$2.95 – $2.95 · 1 providers · max÷min 1.0×
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 |
|---|---|---|---|---|
OpenCode Go subscription plan | $0.30 | $1.20 | $0.00600 | $0.19 |
OpenRouter router / aggregator | $0.30 | $1.20 | $0.00600 | $0.19 |
LongCatfirst-party first-party lab | $0.75 | $2.95 | $0.01 | $0.48 |
Kilo Gateway router / aggregator | $0.75 | $3.00 | $0.01 | $0.49 |
NanoGPT router / aggregator | $0.75 | $3.00 | $0.01 | $0.49 |
Unpriced · 1
Listed at $0 with no published pricing — we can't tell whether it's free, bundled or just missing. Excluded from cheapest, median and spread.
- OpenCode Zen longcat-2.0-freeunpriced
Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.