modelstatus.dev

MiniMax M2: providers compared

Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.

Current state

	State
Googlegoogle-vertex	No data	—	97.51%	100%◆ (best)	99.28%	344ms◆ (best)	1.38s◆ (best)	108 tps◆ (best)	197K	$0.300 / $1.20
Minimaxminimax/fp8fp8	No data	—	99.93%	99.93%	99.90%	718ms	1.59s	81 tps	205K	$0.255 / $1.02◆ (best)
Novitanovita/fp8fp8	No data	—	99.77%	100%◆ (best)	100%◆ (best)	1.27s	9.17s	68 tps	205K	$0.300 / $1.20

Google—
No data24h 97.51%
7d
100%◆ (best)
30d
99.28%
p50
344ms◆ (best)
p99
1.38s◆ (best)
Throughput
108 tps◆ (best)
Context
197K
$/Mtok
$0.300 / $1.20
google-vertex
Minimax—
No data24h 99.93%
7d
99.93%
30d
99.90%
p50
718ms
p99
1.59s
Throughput
81 tps
Context
205K
$/Mtok
$0.255 / $1.02◆ (best)
minimax/fp8fp8
Novita—
No data24h 99.77%
7d
100%◆ (best)
30d
100%◆ (best)
p50
1.27s
p99
9.17s
Throughput
68 tps
Context
205K
$/Mtok
$0.300 / $1.20
novita/fp8fp8

Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.

Price vs latency

One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag

History

Availability

Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.

Time to first token

Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window, averaged over the hour.

Throughput

Median tokens per second.