Skip to content
Sovyron

MiniMax M2.1 Lightning

minimax-m205k context131k max outputreleased Dec 23, 2025Open weightsReasoningTool calling

As of Nov 22, 2026, the cheapest MiniMax M2.1 Lightning API price is $0.12 per 1M input tokens (DevPass (LLM Gateway)) and $0.48 per 1M output tokens (DevPass (LLM Gateway)). MiniMax M2.1 Lightning is offered by 3 providers in the minimax-m family, open weights, reasoning enabled.

Cheapest input
$0.12
Cheapest output
$0.48
Official
—
output per 1M tokens
Providers
3
offering this model
Spread
5.0×
max / min output
Free offers
0
free-tier offers

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked.

MiniMax M2.1 Lightning API prices by provider in USD per 1M tokens, updated Nov 22, 2026
DevPass (LLM Gateway)openminimax-m2.1-lightningCheapest$0.12Cheapest$0.48——197k
LLM Gatewayminimax/minimax-m2.1-lightning$0.12$0.48——197k
Ofoxopenminimax/minimax-m2.1-lightning$0.3$2.4$0.03$0.375205k

MiniMax M2.1 Lightning pricing FAQ

What is the cheapest MiniMax M2.1 Lightning API?

As of Nov 22, 2026, DevPass (LLM Gateway) has the lowest MiniMax M2.1 Lightning output price at $0.48 per 1M tokens, and DevPass (LLM Gateway) has the lowest input price at $0.12 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How many providers offer MiniMax M2.1 Lightning?

3 providers list MiniMax M2.1 Lightning on Sovyron; 3 of them sell it at a metered per-token price.

Is MiniMax M2.1 Lightning free?

No provider in the Sovyron catalog lists a free tier for MiniMax M2.1 Lightning.

What is the context window of MiniMax M2.1 Lightning?

MiniMax M2.1 Lightning supports a 205k-token context window and up to 131k output tokens.

Token cost calculator

What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.

Estimated

—