MiniMax: MiniMax M3 Performance
Try MiniMax M3 on us. Starter credit covers your first requests, then one key reaches all 13 provider routes with automatic failover.
minimax/minimax-m3
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), effective throughput, and success rate for MiniMax: MiniMax M3. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime, and no prompt or output content is stored.
| Provider | p50 TTFT | p95 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| minimax | 1505 ms | 2250 ms | 84 tok/s n=2 | 100.00% | — | 13 |
| telnyx | 902 ms | 902 ms | 222 tok/s n=2 | 100.00% | — | 1 |
| parasail | 974 ms | 1171 ms | 374 tok/s n=2 | 100.00% | — | 2 |
| fireworks | 1940 ms | 1940 ms | 354 tok/s n=2 | 100.00% | — | 1 |
| featherless | 2025 ms | 2025 ms | 204 tok/s n=2 | 100.00% | — | 1 |
| streamlake | 2344 ms | 2344 ms | 85 tok/s n=2 | 100.00% | — | 1 |
| nebius | 3136 ms | 3136 ms | 299 tok/s n=2 | 100.00% | — | 1 |
| wandb | — | — | 230 tok/s n=2 | 100.00% | — | 6 |
| atlas-cloud | — | — | 111 tok/s n=2 | — | — | 0 |
| boundless | — | — | 104 tok/s n=2 | — | — | 0 |
| deepinfra | — | — | 67 tok/s n=2 | — | — | 0 |
| novita | — | — | 102 tok/s n=2 | — | — | 0 |
| siliconflow | — | — | 99 tok/s n=2 | — | — | 0 |
Full provider & model leaderboard.
13 routes.
More routes give the auto router more room to fail over around provider 429 and 5xx responses.
Gateway overhead is measured separately.
Public status separates TLS/health overhead from full model latency so slow LLMs do not inflate the router metric.
Metadata rollups.
Status samples store latency, outcome, provider, model, route, cost, and region metadata only.
View public status or inspect provider routes.