MiniMax M3
minimax/minimax-m3InputOutput
Compare its 14 providersIncident RSSCompare with MiniMax M2.7, MiniMax M2.5, MiniMax M2.1
CompareMiniMax M3
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.90% | 98.70% | 90.50% | 1.11s | 8.16s | 65 tps | 524K | $0.300 / $1.20 | |
| Healthy | 100% | 99.72% | 99.02% | 99.25% | 973ms | 10.6s | 59 tps | 262K | $0.230 / $0.960 | |
| Healthy | 100% | 99.59% | 99.56% | 98.84% | 1.06s | 10.6s | 15 tps | 524K | $0.280 / $1.10 | |
| Healthy | 100% | 99.80% | 99.48% | 99.51% | 2.10s | 8.42s | 58 tps | 1.0M | $0.240 / $0.960 | |
| Healthy | 100% | 99.70% | 99.63% | 99.34% | 1.11s | 11.5s | 70 tps | 524K | $0.300 / $1.20 | |
| Healthy | 100% | 99.38% | 98.39% | 98.96% | 1.67s | 4.55s | 111 tps | 1.0M | $0.750 / $3.00 | |
| Healthy | 100% | 99.55% | 99.56% | 99.62% | 1.91s | 35.1s | 57 tps | 1.0M | $0.300 / $1.20 | |
| Healthy | 100% | 99.35% | 99.51% | 98.41% | 1.06s | 5.65s | 106 tps | 1.0M | $0.300 / $1.20 | |
| Healthy | 97.62% | 98.63% | 98.67% | 99.05% | 2.19s | 10.9s | 55 tps | 1.0M | $0.300 / $1.20 | |
Togethertogether | Degraded | 93.10% | 99.28% | 99.64% | 99.55% | 2.16s | 33.8s | 25 tps | 524K | $0.300 / $1.20 |
Maramara | No data | — | 97.10% | 94.06% | 91.65% | 1.41s | 22.8s | 169 tps | 1.0M | $0.600 / $2.40 |
| No data | — | — | — | — | — | — | — | 256K | $0.255 / $1.02 | |
SambaNovasambanova | No data | — | 96.57% | 96.25% | 97.23% | 1.64s | 10.4s | 77 tps | 1.0M | $0.600 / $2.40 |
| No data | — | 97.02% | 96.29% | 95.28% | 1.10s | 7.73s | 53 tps | 524K | $0.300 / $1.20 |
- AtlasCloud100%Healthy24h 99.90%
- 7d
- 98.70%
- 30d
- 90.50%
- p50
- 1.11s
- p99
- 8.16s
- Throughput
- 65 tps
- Context
- 524K
- $/Mtok
- $0.300 / $1.20
atlas-cloud/fp8fp8 - CoreWeave100%Healthy24h 99.72%
- 7d
- 99.02%
- 30d
- 99.25%
- p50
- 973ms
- p99
- 10.6s
- Throughput
- 59 tps
- Context
- 262K
- $/Mtok
- $0.230 / $0.960
coreweave/fp4fp4 - DeepInfra100%Healthy24h 99.59%
- 7d
- 99.56%
- 30d
- 98.84%
- p50
- 1.06s
- p99
- 10.6s
- Throughput
- 15 tps
- Context
- 524K
- $/Mtok
- $0.280 / $1.10
deepinfra/fp8fp8 - GMICloud100%Healthy24h 99.80%
- 7d
- 99.48%
- 30d
- 99.51%
- p50
- 2.10s
- p99
- 8.42s
- Throughput
- 58 tps
- Context
- 1.0M
- $/Mtok
- $0.240 / $0.960
gmicloud/fp8fp8 - Minimax100%Healthy24h 99.70%
- 7d
- 99.63%
- 30d
- 99.34%
- p50
- 1.11s
- p99
- 11.5s
- Throughput
- 70 tps
- Context
- 524K
- $/Mtok
- $0.300 / $1.20
minimax/fp8fp8 - ModelRun100%Healthy24h 99.38%
- 7d
- 98.39%
- 30d
- 98.96%
- p50
- 1.67s
- p99
- 4.55s
- Throughput
- 111 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.00
modelrun/fp4fp4 - Novita100%Healthy24h 99.55%
- 7d
- 99.56%
- 30d
- 99.62%
- p50
- 1.91s
- p99
- 35.1s
- Throughput
- 57 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
novita/fp8fp8 - Parasail100%Healthy24h 99.35%
- 7d
- 99.51%
- 30d
- 98.41%
- p50
- 1.06s
- p99
- 5.65s
- Throughput
- 106 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
parasail/fp8fp8 - StreamLake97.62%Healthy24h 98.63%
- 7d
- 98.67%
- 30d
- 99.05%
- p50
- 2.19s
- p99
- 10.9s
- Throughput
- 55 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
streamlake/fp8fp8 - Together93.10%Degraded24h 99.28%
- 7d
- 99.64%
- 30d
- 99.55%
- p50
- 2.16s
- p99
- 33.8s
- Throughput
- 25 tps
- Context
- 524K
- $/Mtok
- $0.300 / $1.20
together - Mara—No data24h 97.10%
- 7d
- 94.06%
- 30d
- 91.65%
- p50
- 1.41s
- p99
- 22.8s
- Throughput
- 169 tps
- Context
- 1.0M
- $/Mtok
- $0.600 / $2.40
mara - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 256K
- $/Mtok
- $0.255 / $1.02
morph/fp4fp4 - No data24h 96.57%
- 7d
- 96.25%
- 30d
- 97.23%
- p50
- 1.64s
- p99
- 10.4s
- Throughput
- 77 tps
- Context
- 1.0M
- $/Mtok
- $0.600 / $2.40
sambanova - No data24h 97.02%
- 7d
- 96.29%
- 30d
- 95.28%
- p50
- 1.10s
- p99
- 7.73s
- Throughput
- 53 tps
- Context
- 524K
- $/Mtok
- $0.300 / $1.20
venice/fp8fp8
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint has no chartable data in this range.
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.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 14 endpoints · 47 days with data, 127 endpoint-days below 90%.
Price changes
- MiniMax M3SambaNovasambanova$0.600 / $2.40cache read — → $0.0602026-09-29 15:31 UTC
- MiniMax M3GMICloudgmicloud/fp8$0.300 → $0.240 / $1.20 → $0.960cache read $0.060 → $0.0482026-09-26 00:55 UTC
- MiniMax M3GMICloudgmicloud/fp8$0.240 → $0.300 / $0.960 → $1.20cache read $0.048 → $0.0602026-09-26 00:40 UTC
- MiniMax M3GMICloudgmicloud/fp8$0.300 → $0.240 / $1.20 → $0.960cache read $0.060 → $0.0482026-09-09 10:15 UTC
- MiniMax M3GMICloudgmicloud/fp8$0.240 → $0.300 / $0.960 → $1.20cache read $0.048 → $0.0602026-09-09 10:05 UTC
- MiniMax M3GMICloudgmicloud/fp8$0.120 → $0.240 / $0.480 → $0.960cache read $0.024 → $0.0482026-09-09 06:20 UTC
- MiniMax M3GMICloudgmicloud/fp8$0.240 → $0.120 / $0.960 → $0.480cache read $0.048 → $0.0242026-09-09 01:20 UTC
- MiniMax M3GMICloudgmicloud/fp8$0.600 → $0.240 / $2.40 → $0.960cache read $0.120 → $0.0482026-09-07 07:30 UTC
- MiniMax M3GMICloudgmicloud/fp8$0.240 → $0.600 / $0.960 → $2.40cache read $0.048 → $0.1202026-09-07 07:25 UTC
- MiniMax M3GMICloudgmicloud/fp8$0.600 → $0.240 / $2.40 → $0.960cache read $0.120 → $0.0482026-09-07 07:20 UTC
- MiniMax M3GMICloudgmicloud/fp8$0.240 → $0.600 / $0.960 → $2.40cache read $0.048 → $0.1202026-08-24 16:20 UTC
- MiniMax M3GMICloudgmicloud/fp8$0.600 → $0.240 / $2.40 → $0.960cache read $0.120 → $0.0482026-08-22 01:45 UTC
- MiniMax M3GMICloudgmicloud/fp8$0.240 → $0.600 / $0.960 → $2.40cache read $0.048 → $0.1202026-08-22 01:35 UTC
- MiniMax M3Morphmorph/fp4$0.300 → $0.255 / $1.20 → $1.022026-08-21 01:15 UTC
- MiniMax M3SambaNovasambanovafree → $0.600 / free → $2.402026-08-20 21:35 UTC