MiniMax M3 vs MiniMax M2.7
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 M3MiniMax M2.7
| Model | Providers | Best uptime | Fastest p50 | Best p99 | Throughput | Context | Cheapest $/Mtok |
|---|---|---|---|---|---|---|---|
| MiniMax M3 | 12/12 | 100% AtlasCloud | 667ms CoreWeave | 4.07s AtlasCloud | 140 tps Parasail | 1.0M | $0.230 / $0.960 CoreWeave |
| MiniMax M2.7 | 7/11 | 100% AtlasCloud | 473ms Groq | 2.68s DeepInfra | 220 tps Groq | 205K | $0.240 / $0.960 GMICloud |
Measured 4m ago. Each figure is the best available across that model's providers.
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.