Popular Comparisons:
⚡3-Second Selection Verdict
Daily & TestsPick MiniMax-M3.1-Flash (Save 50%)
MiniMaxVerified

MiniMax-M3.1-Flash

★ Save 50%
Input$0.15 / 1M
Output$0.60 / 1M
Context1M
CursorBench Pass Rate—
MiniMaxVerified

MiniMax-M3

Input$0.30 / 1M
Output$1.20 / 1M
Context1M
CursorBench Pass Rate—
MiniMaxVerified

MiniMax-M2.7

Input$0.30 / 1M
Output$1.20 / 1M
Context1M
CursorBench Pass Rate—

Pick your workflow, then your budget

Estimates use our price snapshot, excluding cache, retries, taxes and tools. Check availability for preview and legacy models.

Workload cost · USD (lower costs less)

MiniMax-M3.1-Flash$2.70
MiniMax-M3$5.40
MiniMax-M2.7$5.40

Context capacity · tokens (not recall accuracy)

MiniMax-M3.1-Flash1,000,000
MiniMax-M31,000,000
MiniMax-M2.71,000,000

CursorBench 4.0 · %

MiniMax-M3.1-FlashNo verified data
MiniMax-M3No verified data
MiniMax-M2.7No verified data

Tool reliability, long-context recall and same-harness SWE-bench: untested, not zero.

CursorBench · 2026-10-20 ↗
Patch review example: why does an empty array slip through?

Editorial example, not measured model output. Review boundary contracts and regression tests; this is not a model ranking.

export function mean(values: number[]) {
  return values.reduce((a, b) => a + b, 0)
    / values.length;
}

// mean([]) => NaN
// Missing an explicit empty-input contract
⚙️ Select ModelMiniMax-M3.1-Flash vs MiniMax-M3 vs MiniMax-M2.7
Slot 1MiniMax
Slot 2MiniMax
Slot 3MiniMax
MiniMax-M3.1-Flash VS MiniMax-M3 VS MiniMax-M2.7
💳 View Plans↗

💰 Monthly Cost Simulation

Simulate monthly cost differences based on your estimated token usage volume

Monthly Input Tokens (Prompt)10 M tokens
Monthly Output Tokens (Completion)2 M tokens
MiniMax-M3.1-Flash
$2.70/ mo
(in: $1.50 + out: $1.20)
MiniMax-M3
$5.40/ mo
(in: $3.00 + out: $2.40)
MiniMax-M2.7
$5.40/ mo
(in: $3.00 + out: $2.40)
AttributeMiniMax-M3.1-FlashMiniMaxMiniMax-M3MiniMaxMiniMax-M2.7MiniMax
Input$0.15$0.30$0.30
Output$0.60$1.20$1.20
Context1M1M1M
CursorBench Pass Rate———
StatusVerifiedVerifiedVerified
Tags & CapabilitiesNew, Fast, Low cost, Coding, Agentic, Open weightsFlagship, Coding, Reasoning, Agentic, Vision, Long contextCoding, Reasoning
LMArena Code#—#42#49
LMArena Agent#—#34#—
CursorBench#—#—#—
Artificial Analysis#17#23#—
Vals AI#16#—#—
LiveBench#15#—#—
LMArena Text#—#50#60
ADSponsored