OpenAI compatible API · Attested · Public status
MiniMax: MiniMax M3 Performance
TrustedRouter performance signals and provider route posture for MiniMax: MiniMax M3.
Onebase URL to migrate
100sof models and routes
Noneprompt logs by default
minimax/minimax-m3
open weights
Performance
AI IQ
IQ 112
#37 public AI IQ rank for minimax-m3
View AI IQ profile
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), throughput, and success rate for MiniMax: MiniMax M3 — unsupported route and probe-configuration rows are separated from provider downtime, and no prompt or output content is stored.
| Provider | p50 TTFT | p95 TTFT | p50 TTFB | Throughput | Uptime | Config excluded | Samples |
|---|---|---|---|---|---|---|---|
| atlas-cloud | 1568 ms | 6591 ms | 1567 ms | — | 100.00% | — | 3 |
| wafer | 4411 ms | 15079 ms | 4410 ms | — | 97.30% | — | 37 |
| morph | 4792 ms | 22581 ms | 4792 ms | — | 95.24% | — | 21 |
| parasail | 4878 ms | 10524 ms | 4878 ms | — | 85.71% | — | 7 |
| minimax | 6400 ms | 19373 ms | 6399 ms | — | 100.00% | — | 29 |
| siliconflow | 8722 ms | 22326 ms | 8722 ms | 12 tok/s | 100.00% | — | 5 |
| deepinfra | 10462 ms | 12016 ms | 10461 ms | — | 100.00% | — | 7 |
Full provider & model leaderboard.
Provider diversity
17 routes.
More routes give the auto router more room to fail over around provider 429 and 5xx responses.
Streaming
Gateway overhead is measured separately.
Public status separates TLS/health overhead from full model latency so slow LLMs do not inflate the router metric.
Status
Metadata rollups.
Status samples store latency, outcome, provider, model, route, cost, and region metadata only.
View public status or inspect provider routes.