MiniMax M2.7: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 99.61% | 98.84% | 98.84% | 4.87s | 55.7s | 4.0 tps | 197K | $0.300 / $1.20 | |
| Healthy | 100%◆ (best) | 99.71% | 99.74%◆ (best) | 99.74%◆ (best) | 541ms | 10.7s | 28 tps | 197K | $0.250 / $1.00 | |
Groqgroq | Healthy | 100%◆ (best) | 99.90% | 99.54% | 99.54% | 274ms◆ (best) | 2.34s◆ (best) | 329 tps◆ (best) | 197K | $0.600 / $1.80 |
Maramara | Healthy | 100%◆ (best) | 99.51% | 99.03% | 99.03% | 1.36s | 6.80s | 116 tps | 197K | $0.240 / $0.960◆ (best) |
| Healthy | 100%◆ (best) | 99.20% | 98.31% | 98.31% | 2.12s | 6.32s | 30 tps | 205K | $0.300 / $1.20 | |
| Healthy | 100%◆ (best) | 91.94% | 97.31% | 97.31% | 1.30s | 9.51s | 44 tps | 205K | $0.600 / $2.40 | |
| Healthy | 100%◆ (best) | 99.27% | 98.26% | 98.26% | 3.42s | 6.20s | 7.0 tps | 205K | $0.270 / $1.08 | |
| Healthy | 99.89% | 99.96% | 99.73% | 99.73% | 3.84s | 6.57s | 6.0 tps | 197K | $0.240 / $0.960◆ (best) | |
| Down | — | 50.13% | 81.20% | 81.20% | 7.42s | 66.9s | 29 tps | 197K | $0.380 / $1.70 | |
Fireworksfireworks | No data | — | 99.19% | 98.88% | 98.88% | 2.89s | 7.73s | 173 tps | 197K | $0.300 / $1.20 |
SambaNovasambanova | No data | — | 90.28% | 99.20% | 99.20% | 10.4s | 72.1s | 6.5 tps | 197K | $0.600 / $2.40 |
- AtlasCloud100%◆ (best)Healthy24h 99.61%
- 7d
- 98.84%
- 30d
- 98.84%
- p50
- 4.87s
- p99
- 55.7s
- Throughput
- 4.0 tps
- Context
- 197K
- $/Mtok
- $0.300 / $1.20
atlas-cloud/fp8fp8 - DeepInfra100%◆ (best)Healthy24h 99.71%
- 7d
- 99.74%◆ (best)
- 30d
- 99.74%◆ (best)
- p50
- 541ms
- p99
- 10.7s
- Throughput
- 28 tps
- Context
- 197K
- $/Mtok
- $0.250 / $1.00
deepinfra/fp8fp8 - Groq100%◆ (best)Healthy24h 99.90%
- 7d
- 99.54%
- 30d
- 99.54%
- p50
- 274ms◆ (best)
- p99
- 2.34s◆ (best)
- Throughput
- 329 tps◆ (best)
- Context
- 197K
- $/Mtok
- $0.600 / $1.80
groq - Mara100%◆ (best)Healthy24h 99.51%
- 7d
- 99.03%
- 30d
- 99.03%
- p50
- 1.36s
- p99
- 6.80s
- Throughput
- 116 tps
- Context
- 197K
- $/Mtok
- $0.240 / $0.960◆ (best)
mara - Minimax100%◆ (best)Healthy24h 99.20%
- 7d
- 98.31%
- 30d
- 98.31%
- p50
- 2.12s
- p99
- 6.32s
- Throughput
- 30 tps
- Context
- 205K
- $/Mtok
- $0.300 / $1.20
minimax/fp8fp8 - Minimax100%◆ (best)Healthy24h 91.94%
- 7d
- 97.31%
- 30d
- 97.31%
- p50
- 1.30s
- p99
- 9.51s
- Throughput
- 44 tps
- Context
- 205K
- $/Mtok
- $0.600 / $2.40
minimax/highspeedfp8 - Novita100%◆ (best)Healthy24h 99.27%
- 7d
- 98.26%
- 30d
- 98.26%
- p50
- 3.42s
- p99
- 6.20s
- Throughput
- 7.0 tps
- Context
- 205K
- $/Mtok
- $0.270 / $1.08
novita/fp8fp8 - GMICloud99.89%Healthy24h 99.96%
- 7d
- 99.73%
- 30d
- 99.73%
- p50
- 3.84s
- p99
- 6.57s
- Throughput
- 6.0 tps
- Context
- 197K
- $/Mtok
- $0.240 / $0.960◆ (best)
gmicloud/fp8fp8 - Down24h 50.13%
- 7d
- 81.20%
- 30d
- 81.20%
- p50
- 7.42s
- p99
- 66.9s
- Throughput
- 29 tps
- Context
- 197K
- $/Mtok
- $0.380 / $1.70
deepinfra/turbofp8 - No data24h 99.19%
- 7d
- 98.88%
- 30d
- 98.88%
- p50
- 2.89s
- p99
- 7.73s
- Throughput
- 173 tps
- Context
- 197K
- $/Mtok
- $0.300 / $1.20
fireworks - No data24h 90.28%
- 7d
- 99.20%
- 30d
- 99.20%
- p50
- 10.4s
- p99
- 72.1s
- Throughput
- 6.5 tps
- Context
- 197K
- $/Mtok
- $0.600 / $2.40
sambanova
Measured 4m 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.