Is BGE M3 or MiniMax-M2.7-highspeed cheaper?

BGE M3 is cheaper on output tokens ($0.00 vs $2.40 per 1M).

Which has the larger context window, BGE M3 or MiniMax-M2.7-highspeed?

MiniMax-M2.7-highspeed has the larger context window (205K tokens).

BGE M3 vs MiniMax-M2.7-highspeed

BGE M3 is cheaper on output tokens, while MiniMax-M2.7-highspeed offers a larger context window. Choose BGE M3 or MiniMax-M2.7-highspeed based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	BGE M3	MiniMax-M2.7-highspeed
Provider	Novita AI	Novita AI
Input / 1M tokens	$0.01	$0.60
Output / 1M tokens	$0.00	$2.40
Context window	8K	205K
Parameters	—	—
Open weights	Yes	Yes
Released	Jan 2024	Mar 2026

BGE M3 details →MiniMax-M2.7-highspeed details →

FAQ

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.