MiniMax M2.1: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| No data | — | 99.75% | 100%◆ (best) | 99.96%◆ (best) | 2.49s | 3.04s | 80 tps◆ (best) | 205K | $0.300 / $1.20◆ (best) | |
| No data | — | 99.32% | 99.87% | 99.94% | 1.09s◆ (best) | 2.74s | 42 tps | 205K | $0.300 / $2.40◆ (best) | |
| No data | — | 99.69% | 99.50% | 99.64% | 1.43s | 1.89s◆ (best) | 41 tps | 205K | $0.300 / $1.20◆ (best) |
- No data24h 99.75%
- 7d
- 100%◆ (best)
- 30d
- 99.96%◆ (best)
- p50
- 2.49s
- p99
- 3.04s
- Throughput
- 80 tps◆ (best)
- Context
- 205K
- $/Mtok
- $0.300 / $1.20◆ (best)
minimax/fp8fp8 - No data24h 99.32%
- 7d
- 99.87%
- 30d
- 99.94%
- p50
- 1.09s◆ (best)
- p99
- 2.74s
- Throughput
- 42 tps
- Context
- 205K
- $/Mtok
- $0.300 / $2.40◆ (best)
minimax/highspeedfp8 - No data24h 99.69%
- 7d
- 99.50%
- 30d
- 99.64%
- p50
- 1.43s
- p99
- 1.89s◆ (best)
- Throughput
- 41 tps
- Context
- 205K
- $/Mtok
- $0.300 / $1.20◆ (best)
novita/fp8fp8
Measured 2m 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.
Throughput
Median tokens per second.