OpenAI compatible API. Attested gateway. Public status.
MiniMax: MiniMax M2.5 Performance
TrustedRouter performance signals and provider route posture for MiniMax: MiniMax M2.5.
1 URLbase_url migration
100smodels and routes
0prompt logs by default
minimax/minimax-m2.5
Performance
AI IQ
IQ 103
#43 public AI IQ rank for minimax-m2.5
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 M2.5 — 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 |
|---|---|---|---|---|---|---|---|
| friendli | 1916 ms | 16976 ms | 1915 ms | — | 100.00% | — | 9 |
| phala | 5361 ms | 20624 ms | 5360 ms | — | 100.00% | — | 12 |
| parasail | 7176 ms | 11458 ms | 7175 ms | — | 100.00% | — | 5 |
| novita | 11180 ms | 11180 ms | 11179 ms | — | 100.00% | — | 1 |
Full provider & model leaderboard.
Provider diversity
9 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.