MiniMax M3 (batch) vs MiniMax M3
One line per model: the best value available from any of its providers at each point, which is what a caller routing to the healthy endpoint would see.
CompareMiniMax M3 (batch)MiniMax M3
| Model | Providers | Best uptime | Fastest p50 | Best p99 | Throughput | Context | Cheapest $/Mtok |
|---|---|---|---|---|---|---|---|
| MiniMax M3 (batch) | 0/1 | — | — | — | — | 524K | $0.300 / $1.20 Together |
| MiniMax M3 | 12/12 | 100% AtlasCloud | 709ms DeepInfra | 8.60s AtlasCloud | 105 tps ModelRun | 1.0M | $0.230 / $0.960 CoreWeave |
History
Availability
Best uptime available from any provider. Axis starts at 90%; it expands to 0 when a model falls below.
Time to first token
Fastest p50 available from any provider. Logarithmic axis.
Throughput
Best median tokens per second available.