What is the cheapest MiniMax model?

MiniMax-M2.7 is currently MiniMax's cheapest paid tracked model at $0.3 per 1M input tokens and $1.2 per 1M output tokens.

How many MiniMax models are tracked?

2 current MiniMax models are tracked, each linked to the official pricing page. The dataset is refreshed twice daily.

Does MiniMax offer cached-input pricing?

MiniMax lists cached-input (prompt-caching) prices for 2 tracked models — cached input is billed at a discount when a prompt prefix repeats.

MiniMax

Commercial provider · 2 models tracked · Founded 2021

Chinese AI lab. The MiniMax-M2 series (M2 through M2.7, plus M3 at 1M context) starts at $0.30/$1.20 per 1M tokens.

MiniMax pricing at a glanceAugust 2026 · $ per 1M tokens

MiniMax API pricing (August 2026): 2 current models range from $0.300 to $0.300 per 1M input tokens and $1.20 to $1.20 per 1M output tokens. The cheapest paid model is MiniMax-M2.7 at $0.300/1M input; the priciest is MiniMax-M3 at $0.300/1M input / $1.20 output. Every price links to MiniMax's official pricing page and refreshes twice daily.

Models2

Input range$0.300–$0.300

Output range$1.20–$1.20

Cached-input tiers2

Today's MiniMax prices

2 models · cheapest blended first

Sorted by blended cost (cheapest first). Prices per 1M tokens, August 2026 — every price links to MiniMax's official pricing page.

Current MiniMax model prices per 1M tokens, sorted by blended cost
Model	Blended*	Input	Output	Cached in	Relative cost	Context	Status
MiniMax-M2.7	$0.525	$0.300	$1.20	$0.060		205K	Current
MiniMax-M3	$0.525	$0.300	$1.20	$0.060		1M	Current

* Blended = (3×input + 1×output) ÷ 4 $/1M tokens · cheap · mid · expensive MODELPRICEWATCH.COM · 2026-08-09

Quick stats

Models tracked: 2
Type: commercial
Founded: 2021
Cheapest model: MiniMax-M2.7
Cheapest blended: $0.525/M

Open-weight models

2 open-weight models available from this provider.

MiniMax-M2.7

$0.300/M in · 205K ctx

MiniMax-M3

$0.300/M in · 1M ctx

Try MiniMax

Get started

Run it yourself

Self-host MiniMax's open-weight models

These models ship with open weights, so you can serve them yourself on rented GPUs instead of paying per-token API prices — often cheaper at scale.

RunPod →

Rent GPUs by the second and serve any open-weight model yourself.

Novita AI →

Serverless open-model inference billed per token — no GPU ops.

Vast.ai →

GPU marketplace — rent spot/on-demand GPUs cheaply and serve any open-weight model.

Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.