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.
| MODEL | INPUT $/1M | CACHED IN | OUTPUT $/1M | BLENDED | CONTEXT | YOUR COST |
|---|---|---|---|---|---|---|
MiniMax M3 MiniMax-M3 · promo price | $0.30 | $0.06 | $1.20 | $0.525 | 1.05M | $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.
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.
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.
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.
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.
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.
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
ReqKey gives every key a credit balance — validate, deduct, enforce limits, and watch per-consumer MiniMax spend in real time.