FREE TOOL · PRICES VERIFIED AUGUST 31, 2026

MiniMax API Pricing

An open multimodal model with a 1M-token window at small-model prices — currently on promotion. Real per-million-token rates, a workload calculator, and the budget-tier comparisons.

MODELS
2
INPUT FROM
$0.30/1M
OUTPUT UP TO
$1.20/1M
MAX CONTEXT
1.05M
ESTIMATE YOUR WORKLOAD
MODELINPUT $/1MCACHED INOUTPUT $/1MBLENDEDCONTEXTYOUR COST
MiniMax M3
MiniMax-M3 · promo price
$0.30$0.06$1.20$0.5251.05M$0.90
MiniMax M2.7
MiniMax-M2.7
$0.30$0.06$1.20$0.525$0.90

USD per 1M tokens from MiniMax’s official pricing page as of August 31, 2026. Blended assumes a 3:1 input:output ratio. Get keys at the MiniMax console.

HOW MINIMAX PRICING WORKS

Mid-tier capability at small-tier prices — while the promo lasts.

MiniMax M3 costs $0.30 input / $1.20 output per 1M tokens — promotional pricing, flagged in the table — for a reasoning model that takes images and video in a 1.05M-token context, with open weights. That is small-model money for a genuinely mid-tier multimodal model.

M2.7, the previous generation, sits at the same price point but is text-only and does not publish a context window. Unless you are pinned to it, M3 is the obvious pick of the two.

Cache reads bill at $0.06 per 1M tokens on both models — a fifth of fresh input. The usual promo caveat applies: promotional rates can end, so check the verification date stamped above before budgeting long-term.

How much does the MiniMax API cost?

MiniMax M3 and M2.7 both cost $0.30 input / $1.20 output per 1M tokens under current promotional pricing, with cache reads at $0.06. M3 adds image and video input and a 1.05M-token context.

Is the MiniMax price a promotion?

Yes — the listed M3 rate is promotional, and promotional rates can change. We verify prices against the official MiniMax pricing page and stamp the date at the top of this page; treat long-term budgets with that in mind.

How does MiniMax M3 compare to other budget models?

At $0.53/1M blended it undercuts DeepSeek V4 Flash ($0.66) and Gemini Flash-Lite ($0.85) while offering video input and a bigger context than either. GLM-5.3-Flash is the one model meaningfully cheaper ($0.12 blended) with a similar modality surface.

Can I self-host MiniMax models?

M3 ships open weights, so yes — self-hosting and third-party inference providers are both options. The rates here are the first-party API prices from platform.minimax.io.

HOW MINIMAX STACKS UP

MiniMax vs. its closest rivals, tier by tier

BLENDED $/1M · 3:1 IN:OUT
BUDGET MULTIMODAL
MiniMax M3
$0.525/1M
GLM-5.3-Flash
$0.119/1M
Gemini 3.5 Flash-Lite
$0.85/1M
COMPARE
VS CLOSED SMALL
MiniMax M3
$0.525/1M
GPT-5.6 Luna
$0.45/1M
Claude Haiku 4.5
$2.00/1M
COMPARE
OPEN VALUE
MiniMax M2.7
$0.525/1M
MiMo-V2.5-Pro
$0.377/1M
DeepSeek V4 Flash
$0.66/1M
COMPARE

Also see: OpenAI API pricing · Claude API pricing · Gemini API pricing · Grok API pricing · DeepSeek API pricing · Kimi API pricing · GLM API pricing · MiMo API pricing · all 58 models

BUILDING ON THE MINIMAX API?

Your users will spend these tokens. Meter them per API key.

ReqKey gives every key a credit balance — validate, deduct, enforce limits, and watch per-consumer MiniMax spend in real time.