OpenAI compatible API · Attested · Public status
MiniMax: MiniMax M2.5 Performance
TrustedRouter performance signals and provider route posture for MiniMax: MiniMax M2.5.
Onebase URL to migrate
100sof models and routes
Noneprompt logs by default
minimax/minimax-m2.5
Performance
AI IQ
IQ 106
#52 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 |
|---|---|---|---|---|---|---|---|
| digitalocean | 2062 ms | 3201 ms | 2062 ms | — | 100.00% | — | 3 |
| atlas-cloud | 2235 ms | 7455 ms | 2234 ms | — | 100.00% | — | 5 |
| novita | 4265 ms | 4265 ms | 4265 ms | — | 100.00% | — | 1 |
| parasail | 5081 ms | 16316 ms | 5081 ms | — | 100.00% | — | 6 |
| friendli | 5165 ms | 18558 ms | 5165 ms | — | 100.00% | — | 23 |
| chutes | 7898 ms | 15618 ms | 7897 ms | — | 86.67% | — | 15 |
Full provider & model leaderboard.
Provider diversity
16 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.