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% | 99.87% | 98.62% | 90.46% | 1.11s | 5.45s | 55 tps | 524K | $0.300 / $1.20 | |
| Healthy | 100% | 99.71% | 99.00% | 99.26% | 895ms | 14.4s | 36 tps | 262K | $0.230 / $0.960 | |
| Healthy | 100% | 99.29% | 98.33% | 98.93% | 468ms | 2.59s | 139 tps | 1.0M | $0.750 / $3.00 | |
Togethertogether | Healthy | 100% | 99.20% | 99.66% | 99.55% | 884ms | 4.31s | 39 tps | 524K | $0.300 / $1.20 |
| Healthy | 100% | 96.87% | 96.26% | 95.31% | 773ms | 3.58s | 76 tps | 524K | $0.300 / $1.20 | |
| Healthy | 99.68% | 99.78% | 99.46% | 99.48% | 1.99s | 7.73s | 33 tps | 1.0M | $0.240 / $0.960 | |
| Healthy | 99.52% | 99.73% | 99.64% | 99.32% | 939ms | 7.16s | 82 tps | 524K | $0.300 / $1.20 | |
| Healthy | 97.37% | 99.58% | 99.58% | 99.61% | 1.15s | 7.30s | 64 tps | 1.0M | $0.300 / $1.20 | |
| Healthy | 96.72% | 99.49% | 99.57% | 98.83% | 2.35s | 8.51s | 12 tps | 524K | $0.280 / $1.10 | |
| Healthy | 96.00% | 98.55% | 98.71% | 99.01% | 1.52s | 8.52s | 43 tps | 1.0M | $0.300 / $1.20 | |
Maramara | No data | — | 97.89% | 94.03% | 91.62% | 1.11s | 36.6s | 136 tps | 1.0M | $0.600 / $2.40 |
| No data | — | — | — | — | — | — | — | 256K | $0.255 / $1.02 | |
| No data | — | 99.35% | 99.50% | 98.41% | 8.09s | 34.7s | 55 tps | 1.0M | $0.300 / $1.20 | |
SambaNovasambanova | No data | — | 95.80% | 96.26% | 97.24% | 1.81s | 10.7s | 74 tps | 1.0M | $0.600 / $2.40 |
- AtlasCloud100%Healthy24h 99.87%
- 7d
- 98.62%
- 30d
- 90.46%
- p50
- 1.11s
- p99
- 5.45s
- Throughput
- 55 tps
- Context
- 524K
- $/Mtok
- $0.300 / $1.20
atlas-cloud/fp8fp8 - CoreWeave100%Healthy24h 99.71%
- 7d
- 99.00%
- 30d
- 99.26%
- p50
- 895ms
- p99
- 14.4s
- Throughput
- 36 tps
- Context
- 262K
- $/Mtok
- $0.230 / $0.960
coreweave/fp4fp4 - ModelRun100%Healthy24h 99.29%
- 7d
- 98.33%
- 30d
- 98.93%
- p50
- 468ms
- p99
- 2.59s
- Throughput
- 139 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $3.00
modelrun/fp4fp4 - Together100%Healthy24h 99.20%
- 7d
- 99.66%
- 30d
- 99.55%
- p50
- 884ms
- p99
- 4.31s
- Throughput
- 39 tps
- Context
- 524K
- $/Mtok
- $0.300 / $1.20
together - Venice100%Healthy24h 96.87%
- 7d
- 96.26%
- 30d
- 95.31%
- p50
- 773ms
- p99
- 3.58s
- Throughput
- 76 tps
- Context
- 524K
- $/Mtok
- $0.300 / $1.20
venice/fp8fp8 - GMICloud99.68%Healthy24h 99.78%
- 7d
- 99.46%
- 30d
- 99.48%
- p50
- 1.99s
- p99
- 7.73s
- Throughput
- 33 tps
- Context
- 1.0M
- $/Mtok
- $0.240 / $0.960
gmicloud/fp8fp8 - Minimax99.52%Healthy24h 99.73%
- 7d
- 99.64%
- 30d
- 99.32%
- p50
- 939ms
- p99
- 7.16s
- Throughput
- 82 tps
- Context
- 524K
- $/Mtok
- $0.300 / $1.20
minimax/fp8fp8 - Novita97.37%Healthy24h 99.58%
- 7d
- 99.58%
- 30d
- 99.61%
- p50
- 1.15s
- p99
- 7.30s
- Throughput
- 64 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
novita/fp8fp8 - DeepInfra96.72%Healthy24h 99.49%
- 7d
- 99.57%
- 30d
- 98.83%
- p50
- 2.35s
- p99
- 8.51s
- Throughput
- 12 tps
- Context
- 524K
- $/Mtok
- $0.280 / $1.10
deepinfra/fp8fp8 - StreamLake96.00%Healthy24h 98.55%
- 7d
- 98.71%
- 30d
- 99.01%
- p50
- 1.52s
- p99
- 8.52s
- Throughput
- 43 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
streamlake/fp8fp8 - Mara—No data24h 97.89%
- 7d
- 94.03%
- 30d
- 91.62%
- p50
- 1.11s
- p99
- 36.6s
- Throughput
- 136 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 99.35%
- 7d
- 99.50%
- 30d
- 98.41%
- p50
- 8.09s
- p99
- 34.7s
- Throughput
- 55 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
parasail/fp8fp8 - No data24h 95.80%
- 7d
- 96.26%
- 30d
- 97.24%
- p50
- 1.81s
- p99
- 10.7s
- Throughput
- 74 tps
- Context
- 1.0M
- $/Mtok
- $0.600 / $2.40
sambanova
Measured 1m 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, averaged over the hour.
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 · 46 days with data, 128 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