MiniMax M3
minimax/minimax-m3
Compare with MiniMax M2.7, MiniMax M2.5, MiniMax M3 (batch)
CompareMiniMax M3
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
AtlasCloudatlas-cloud/fp8fp8 | Healthy | 100% | 99.29% | 802ms | 5.89s | 78 tps | 524K | $0.300 / $1.20 |
CoreWeavecoreweave/fp4fp4 | Healthy | 100% | 98.58% | 675ms | 3.10s | 49 tps | 262K | $0.230 / $0.960 |
GMICloudgmicloud/fp8fp8 | Healthy | 100% | 99.14% | 3.15s | 8.57s | 46 tps | 1.0M | $0.240 / $0.960 |
Morphmorph/fp4fp4 | Healthy | 100% | 94.92% | 1.68s | 10.2s | 32 tps | 256K | $0.300 / $1.20 |
Venicevenice/fp8fp8 | Healthy | 100% | 99.82% | 1.02s | 6.62s | 104 tps | 524K | $0.300 / $1.20 |
Minimaxminimax/fp8fp8 | Healthy | 99.92% | 99.55% | 1.13s | 11.8s | 74 tps | 524K | $0.300 / $1.20 |
Togethertogether | Healthy | 99.71% | 99.63% | 771ms | 8.82s | 65 tps | 524K | $0.300 / $1.20 |
Novitanovita/fp8fp8 | Healthy | 99.63% | 99.49% | 1.73s | 19.2s | 58 tps | 1.0M | $0.300 / $1.20 |
DeepInfradeepinfra/fp8fp8 | Healthy | 99.50% | 97.95% | 675ms | 46.8s | 29 tps | 524K | $0.280 / $1.10 |
ModelRunmodelrun/fp4fp4 | Healthy | 98.63% | 99.21% | 1.87s | 21.0s | 122 tps | 1.0M | $0.750 / $3.00 |
StreamLakestreamlake/fp8fp8 | Healthy | 97.40% | 98.63% | 1.69s | 15.4s | 80 tps | 1.0M | $0.300 / $1.20 |
Parasailparasail/fp8fp8 | Degraded | 93.27% | 98.12% | 747ms | 19.9s | 96 tps | 1.0M | $0.300 / $1.20 |
- AtlasCloud100%Healthy24h 99.29%
- p50
- 802ms
- p99
- 5.89s
- Throughput
- 78 tps
- Context
- 524K
- $/Mtok
- $0.300 / $1.20
atlas-cloud/fp8fp8 - CoreWeave100%Healthy24h 98.58%
- p50
- 675ms
- p99
- 3.10s
- Throughput
- 49 tps
- Context
- 262K
- $/Mtok
- $0.230 / $0.960
coreweave/fp4fp4 - GMICloud100%Healthy24h 99.14%
- p50
- 3.15s
- p99
- 8.57s
- Throughput
- 46 tps
- Context
- 1.0M
- $/Mtok
- $0.240 / $0.960
gmicloud/fp8fp8 - Morph100%Healthy24h 94.92%
- p50
- 1.68s
- p99
- 10.2s
- Throughput
- 32 tps
- Context
- 256K
- $/Mtok
- $0.300 / $1.20
morph/fp4fp4 - Venice100%Healthy24h 99.82%
- p50
- 1.02s
- p99
- 6.62s
- Throughput
- 104 tps
- Context
- 524K
- $/Mtok
- $0.300 / $1.20
venice/fp8fp8 - Minimax99.92%Healthy24h 99.55%
- p50
- 1.13s
- p99
- 11.8s
- Throughput
- 74 tps
- Context
- 524K
- $/Mtok
- $0.300 / $1.20
minimax/fp8fp8 - Together99.71%Healthy24h 99.63%
- p50
- 771ms
- p99
- 8.82s
- Throughput
- 65 tps
- Context
- 524K
- $/Mtok
- $0.300 / $1.20
together - Novita99.63%Healthy24h 99.49%
- p50
- 1.73s
- p99
- 19.2s
- Throughput
- 58 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
novita/fp8fp8 - DeepInfra99.50%Healthy24h 97.95%
- p50
- 675ms
- p99
- 46.8s
- Throughput
- 29 tps
- Context
- 524K
- $/Mtok
- $0.280 / $1.10
deepinfra/fp8fp8 - ModelRun98.63%Healthy24h 99.21%
- p50
- 1.87s
- p99
- 21.0s
- Throughput
- 122 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.00
modelrun/fp4fp4 - StreamLake97.40%Healthy24h 98.63%
- p50
- 1.69s
- p99
- 15.4s
- Throughput
- 80 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
streamlake/fp8fp8 - Parasail93.27%Degraded24h 98.12%
- p50
- 747ms
- p99
- 19.9s
- Throughput
- 96 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
parasail/fp8fp8
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.