MiniMax API pricing: every model, every rate

MiniMax ships a compact family with a notable gap between standard and highspeed variants — the latter bills several times more for lower latency.

Check current 0rates → Free to sign up · $1 minimum top-up · No prepayment

Full rate card

6 billable models. 0 carry a rate verified against the vendor's own published pricing; the rest are gateway rates only. USD per 1M tokens, verified 2026-09-16.

ModelInputOutputOut/InOfficial (in / out)
MiniMax-M2.7-highspeed$2.1$8.44.0×not verified
MiniMax-M2$1.05$4.24.0×not verified
MiniMax-M2.1$1.05$4.24.0×not verified
MiniMax-M2.5$0.15$0.64.0×not verified
MiniMax-M2.7$0.15$0.64.0×not verified
MiniMax-M3$0.15$0.64.0×not verified

Output is billed at a multiple of input on most models. The Out/In column is that multiple — it matters more than the input price once output dominates your bill.

Across 6 billable models the rate spans $0.15 (MiniMax-M2.5) to $2.1 (MiniMax-M2.7-highspeed) per million input tokens — a 14× spread. Picking the wrong tier is usually the single most expensive mistake here.

What MiniMax is good at

MiniMax is competitive for high-volume chat and character-style applications.

Before you compare: Highspeed variants bill at a significant premium. Only worth it when latency is on the critical path.

Create free account

See all 827 models → or use the cost calculator with your own token split.