MiniMax M3
minimax/minimax-m3
Compare with MiniMax M2.7, MiniMax M2.5, MiniMax M3 (batch)
CompareMiniMax M3
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.68% | 97.24% | 97.24% | 511ms | 2.90s | 84 tps | 262K | $0.230 / $0.960 | |
| Healthy | 100% | 99.53% | 99.63% | 99.63% | 1.61s | 18.0s | 52 tps | 524K | $0.300 / $1.20 | |
| Healthy | 100% | 99.76% | 99.76% | 99.76% | 1.22s | 9.53s | 145 tps | 1.0M | $0.750 / $3.00 | |
| Healthy | 100% | 96.60% | 97.49% | 97.49% | 1.34s | 20.5s | 19 tps | 256K | $0.255 / $1.02 | |
SambaNovasambanova | Healthy | 100% | 97.26% | 98.38% | 98.38% | 2.50s | 10.6s | 171 tps | 1.0M | $0.600 / $2.40 |
Togethertogether | Healthy | 100% | 99.78% | 99.78% | 99.78% | 771ms | 6.43s | 75 tps | 524K | $0.300 / $1.20 |
| Healthy | 100% | 99.82% | 99.87% | 99.87% | 1.28s | 12.6s | 108 tps | 524K | $0.300 / $1.20 | |
| Healthy | 99.78% | 99.51% | 99.33% | 99.33% | 3.60s | 10.6s | 34 tps | 1.0M | $0.240 / $0.960 | |
| Healthy | 99.75% | 98.35% | 97.91% | 97.91% | 1.19s | 17.3s | 46 tps | 1.0M | $0.300 / $1.20 | |
| Healthy | 99.38% | 99.64% | 99.66% | 99.66% | 2.40s | 22.2s | 36 tps | 1.0M | $0.300 / $1.20 | |
| Healthy | 98.59% | 99.02% | 98.46% | 98.46% | 1.76s | 8.61s | 49 tps | 1.0M | $0.300 / $1.20 | |
| Healthy | 98.37% | 99.71% | 99.52% | 99.52% | 1.33s | 6.04s | 105 tps | 524K | $0.300 / $1.20 | |
| Healthy | 95.32% | 98.43% | 98.38% | 98.38% | 702ms | 9.65s | 29 tps | 524K | $0.280 / $1.10 |
- CoreWeave100%Healthy24h 99.68%
- 7d
- 97.24%
- 30d
- 97.24%
- p50
- 511ms
- p99
- 2.90s
- Throughput
- 84 tps
- Context
- 262K
- $/Mtok
- $0.230 / $0.960
coreweave/fp4fp4 - Minimax100%Healthy24h 99.53%
- 7d
- 99.63%
- 30d
- 99.63%
- p50
- 1.61s
- p99
- 18.0s
- Throughput
- 52 tps
- Context
- 524K
- $/Mtok
- $0.300 / $1.20
minimax/fp8fp8 - ModelRun100%Healthy24h 99.76%
- 7d
- 99.76%
- 30d
- 99.76%
- p50
- 1.22s
- p99
- 9.53s
- Throughput
- 145 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.00
modelrun/fp4fp4 - Morph100%Healthy24h 96.60%
- 7d
- 97.49%
- 30d
- 97.49%
- p50
- 1.34s
- p99
- 20.5s
- Throughput
- 19 tps
- Context
- 256K
- $/Mtok
- $0.255 / $1.02
morph/fp4fp4 - SambaNova100%Healthy24h 97.26%
- 7d
- 98.38%
- 30d
- 98.38%
- p50
- 2.50s
- p99
- 10.6s
- Throughput
- 171 tps
- Context
- 1.0M
- $/Mtok
- $0.600 / $2.40
sambanova - Together100%Healthy24h 99.78%
- 7d
- 99.78%
- 30d
- 99.78%
- p50
- 771ms
- p99
- 6.43s
- Throughput
- 75 tps
- Context
- 524K
- $/Mtok
- $0.300 / $1.20
together - Venice100%Healthy24h 99.82%
- 7d
- 99.87%
- 30d
- 99.87%
- p50
- 1.28s
- p99
- 12.6s
- Throughput
- 108 tps
- Context
- 524K
- $/Mtok
- $0.300 / $1.20
venice/fp8fp8 - GMICloud99.78%Healthy24h 99.51%
- 7d
- 99.33%
- 30d
- 99.33%
- p50
- 3.60s
- p99
- 10.6s
- Throughput
- 34 tps
- Context
- 1.0M
- $/Mtok
- $0.240 / $0.960
gmicloud/fp8fp8 - Parasail99.75%Healthy24h 98.35%
- 7d
- 97.91%
- 30d
- 97.91%
- p50
- 1.19s
- p99
- 17.3s
- Throughput
- 46 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
parasail/fp8fp8 - Novita99.38%Healthy24h 99.64%
- 7d
- 99.66%
- 30d
- 99.66%
- p50
- 2.40s
- p99
- 22.2s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
novita/fp8fp8 - StreamLake98.59%Healthy24h 99.02%
- 7d
- 98.46%
- 30d
- 98.46%
- p50
- 1.76s
- p99
- 8.61s
- Throughput
- 49 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
streamlake/fp8fp8 - AtlasCloud98.37%Healthy24h 99.71%
- 7d
- 99.52%
- 30d
- 99.52%
- p50
- 1.33s
- p99
- 6.04s
- Throughput
- 105 tps
- Context
- 524K
- $/Mtok
- $0.300 / $1.20
atlas-cloud/fp8fp8 - DeepInfra95.32%Healthy24h 98.43%
- 7d
- 98.38%
- 30d
- 98.38%
- p50
- 702ms
- p99
- 9.65s
- Throughput
- 29 tps
- Context
- 524K
- $/Mtok
- $0.280 / $1.10
deepinfra/fp8fp8
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
Price changes
- MiniMax M3Morphmorph/fp4$0.300 / $1.20 → $0.255 / $1.022026-08-21 01:15 UTC
- MiniMax M3SambaNovasambanovafree / free → $0.600 / $2.402026-08-20 21:35 UTC
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.