Morph V3 Fast
morph/morph-v3-fast
morph· 2025-07-07· 16K ctx
API only quant: unknown
spread (output, p90 ÷ p10)
— too few providers
$1.20 – $1.20 · 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 |
|---|---|---|---|---|
Kilo Gateway router / aggregator | $0.80 | $1.20 | — | $0.84no cache price published |
Morph first-party lab | $0.80 | $1.20 | — | $0.84no cache price published |
OpenRouter router / aggregator | $0.80 | $1.20 | — | $0.84no cache price published |
Vercel AI Gateway router / aggregator | $0.80 | $1.20 | — | $0.84no cache price published |
AI/ML API unclassified | $1.10 | $1.65 | — | $1.15no cache price published |
Data: models.dev (MIT), snapshot 2026-10-17. Prices are vendor-published; verify before purchase. Methodology.