Data updated 2026-10-19.
Price spread

MiniMax M3.1 Flash

minimaxai/minimax-m3.1-flash

minimaxai· 1M ctx
open weightstool callreasoning quant: unknown

spread (output, p90 ÷ p10)

— too few providers

$0.600 – $0.600 · 1 providers · max÷min 1.0×

1 provider priced · 2 offerings

Cheapest / median / spread use providers that serve the model on their own capacity: first-party lab, hyperscaler, inference host.

Provider classes in the stats:
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.

ProviderInputOutputCache rdBlended
MiniMax (minimax.io)
first-party lab
$0.150$0.600$0.0150$0.105
Subscription plans (flat fee, not per-token) · 4

Flat-fee plan — the per-token price is bundled into a subscription, so $0/token is not free. Excluded from cheapest, median and spread.

  • MiniMax Token Plan (minimax.cn) MiniMax-M3.1-FlashMainland-China endpointsubscription plan
  • MiniMax Token Plan (minimax.cn) MiniMax-M3.1-Flash-PreviewMainland-China endpointsubscription plan
  • MiniMax Token Plan (minimax.io) MiniMax-M3.1-Flashsubscription plan
  • MiniMax Token Plan (minimax.io) MiniMax-M3.1-Flash-Previewsubscription plan

Data: models.dev (MIT), snapshot 2026-10-19. Prices are vendor-published; verify before purchase. Methodology.