Latest offers Verdent AI: Subscription streak bonus (+10% up to a +20% cap) View all →
← Brands

Developer: MiniMax · API distributor: Novita AI · API model

MiniMax M3 uses input-length tiers: 1–524,288 tokens costs $0.30/$1.20/$0.06 for input/output/cache read; 524,288–1,000,000 costs $0.60/$2.40/$0.12 per million tokens. Tier boundaries follow the official model page; no flat rate is assigned.

Catalog information only; CreditsPlan does not run inference with this model.

API models and prices · 1

Usage-based billing: text rates are usually per million tokens; other units and tiers are stated per entry. Compare only the same currency, unit and billing conditions. Unverified cache pricing does not mean free.

MiniMax M3

Official model ID: minimax/minimax-m3

Input / output: text, image, video → text

Model developer: MiniMax · Service provider: Novita AI · Market: com

Model family: — · Model catalog only; see service-channel quotes

MiniMax M3 uses input-length tiers: 1–524,288 tokens costs $0.30/$1.20/$0.06 for input/output/cache read; 524,288–1,000,000 costs $0.60/$2.40/$0.12 per million tokens. Tier boundaries follow the official model page; no flat rate is assigned.

Documented API context: 1,000,000 tokens

Maximum output: 131,072 tokens

Requires a Novita AI account and API key. Availability and rate limits depend on the account.

Official source · Last verified: 2026-10-15T06:57:32.742Z

Service channels / prices and conditions

No published matching channel quote is available. Check the model status and official sources.

服务渠道 / 价格与条件

暂无可公开的匹配渠道报价，请查看模型状态与官方来源。