MiniMax M2.5: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
DigitalOceandigitalocean | Healthy | 100%◆ (best) | 99.91% | 99.87% | 99.87% | 706ms | 4.57s | 46 tps | 66K | $0.300 / $1.20 |
Friendlifriendli | Healthy | 100%◆ (best) | 99.67% | 99.95% | 99.95% | 507ms◆ (best) | 1.36s◆ (best) | 98 tps◆ (best) | 197K | $0.300 / $1.20 |
StreamLakestreamlake | Healthy | 100%◆ (best) | 99.88% | 99.93% | 99.93% | 815ms | 3.62s | 55 tps | 200K | $0.270 / $1.08 |
| No data | — | 99.79% | 99.86% | 99.86% | 1.46s | 8.05s | 57 tps | 197K | $0.295 / $1.20 | |
| No data | — | — | 99.99% | 99.99% | — | — | — | 197K | $0.220 / $0.900◆ (best) | |
| No data | — | 99.77% | 99.81% | 99.81% | 1.00s | 4.14s | 62 tps | 205K | $0.300 / $1.20 | |
| No data | — | 99.34% | 100%◆ (best) | 100%◆ (best) | 2.12s | 7.40s | 38 tps | 205K | $0.600 / $2.40 | |
| No data | — | 99.84% | 99.83% | 99.83% | 1.14s | 4.87s | 50 tps | 205K | $0.300 / $1.20 | |
| No data | — | 100% | 100%◆ (best) | 100%◆ (best) | 1.39s | 3.14s | 45 tps | 197K | $0.300 / $1.20 | |
Venicevenice | No data | — | 99.56% | 99.81% | 99.81% | 1.03s | 5.16s | 52 tps | 198K | $0.270 / $0.950 |
- DigitalOcean100%◆ (best)Healthy24h 99.91%
- 7d
- 99.87%
- 30d
- 99.87%
- p50
- 706ms
- p99
- 4.57s
- Throughput
- 46 tps
- Context
- 66K
- $/Mtok
- $0.300 / $1.20
digitalocean - Friendli100%◆ (best)Healthy24h 99.67%
- 7d
- 99.95%
- 30d
- 99.95%
- p50
- 507ms◆ (best)
- p99
- 1.36s◆ (best)
- Throughput
- 98 tps◆ (best)
- Context
- 197K
- $/Mtok
- $0.300 / $1.20
friendli - StreamLake100%◆ (best)Healthy24h 99.88%
- 7d
- 99.93%
- 30d
- 99.93%
- p50
- 815ms
- p99
- 3.62s
- Throughput
- 55 tps
- Context
- 200K
- $/Mtok
- $0.270 / $1.08
streamlake - No data24h 99.79%
- 7d
- 99.86%
- 30d
- 99.86%
- p50
- 1.46s
- p99
- 8.05s
- Throughput
- 57 tps
- Context
- 197K
- $/Mtok
- $0.295 / $1.20
atlas-cloud/fp8fp8 - No data24h —
- 7d
- 99.99%
- 30d
- 99.99%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 197K
- $/Mtok
- $0.220 / $0.900◆ (best)
inceptron/fp8fp8 - No data24h 99.77%
- 7d
- 99.81%
- 30d
- 99.81%
- p50
- 1.00s
- p99
- 4.14s
- Throughput
- 62 tps
- Context
- 205K
- $/Mtok
- $0.300 / $1.20
minimax/fp8fp8 - No data24h 99.34%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 2.12s
- p99
- 7.40s
- Throughput
- 38 tps
- Context
- 205K
- $/Mtok
- $0.600 / $2.40
minimax/highspeedfp8 - No data24h 99.84%
- 7d
- 99.83%
- 30d
- 99.83%
- p50
- 1.14s
- p99
- 4.87s
- Throughput
- 50 tps
- Context
- 205K
- $/Mtok
- $0.300 / $1.20
novita/fp8fp8 - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 1.39s
- p99
- 3.14s
- Throughput
- 45 tps
- Context
- 197K
- $/Mtok
- $0.300 / $1.20
siliconflow/fp8fp8 - No data24h 99.56%
- 7d
- 99.81%
- 30d
- 99.81%
- p50
- 1.03s
- p99
- 5.16s
- Throughput
- 52 tps
- Context
- 198K
- $/Mtok
- $0.270 / $0.950
venice
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.
Throughput
Median tokens per second.