Skip to content
AuraMatrix
← All models

Price comparison

DeepSeek V4.1 Flash vs MiniMax M3.1 Flash: API price

As of 2026-11-15, DeepSeek V4.1 Flash costs $0.30 per 1M input tokens and $1.20 per 1M output tokens; MiniMax M3.1 Flash costs $0.15 and $0.60 (official list prices). On a blend of 3 parts input to 1 part output, MiniMax M3.1 Flash is 50% cheaper than DeepSeek V4.1 Flash. Source: AuraMatrix; list prices as published by each vendor, not invoices.

Side by side

USD per 1M tokens on each vendor’s own API, standard plan. The lower figure in a row is marked.
DeepSeek V4.1 FlashDeepSeekMiniMax M3.1 FlashMiniMax
Input$0.30$0.15
Output$1.20$0.60
Cached input$0.006$0.015
Blend, 3 input : 1 output$0.525$0.2625
A job of 1M input and 250k output tokens$0.60$0.30
Lowest input price on any channel$0.0507OpenRouter$0.075OpenRouter
Time to first token, medianmeasured hourly from Los Angeles1.0 s1.2 s
Output speed—155 tokens/s

Price is one side of the choice: the two models differ in what they can do, and this page does not rank that. A dash means not recorded, never free. Every channel, plan and source is on each model’s own page: DeepSeek V4.1 Flash · MiniMax M3.1 Flash

In your AIAsk your assistant: “Is DeepSeek V4.1 Flash or MiniMax M3.1 Flash cheaper for my workload, and which is faster?”Connect in one click →

More comparisons