MiniMax M2.7 Highspeed

PRICE / USD

$0.6

Per 1 million output tokens · input billed separately

Input / 1M tokens

$0.6

Output / 1M tokens

$2.4

Cached input / 1M tokens

$0.06

Cache write / 1M tokens

$0.375

This is the Highspeed variant; standard M2.7 has a different price.

SPEED & CAPABILITIES

Not benchmarked

Provider description: ≈100 tokens/s. This does not qualify for the numeric (fast) badge.

Approximate provider-reported throughput, not an independently measured rate.

Our own output-speed measurement

Not measured

Context window

204,800

API model ID

MiniMax-M2.7-highspeed

No reviewed Intelligence Index score for this exact model version and setting.

Still listed as available in the official model guide.

Suggested starting role: everyday coding. The documented Highspeed serving option targets M2.7 coding and agent work. Consider it when iteration time matters, while checking actual latency in your environment. This is editorial guidance, not a benchmark score.