OpenAI compatible API · Attested · Public status

MiniMax: MiniMax M3 Performance

TrustedRouter performance signals and provider route posture for MiniMax: MiniMax M3.

Verify gateway
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.

minimax/minimax-m3

open weights Performance

All models

AI IQ IQ 114 #33 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), 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.

Providerp50 TTFTp95 TTFTp50 TTFBEffective throughputUptimeConfig excludedAvailability samples
minimax 1495 ms 2133 ms 1494 ms 100.00% 2
fireworks 1688 ms 3938 ms 1688 ms 100.00% 3
parasail 1727 ms 1727 ms 1727 ms 100.00% 1
wafer 2056 ms 2227 ms 2055 ms 100.00% 7
siliconflow 4336 ms 4336 ms 4336 ms 100.00% 1
atlas-cloud 0.00% 1
morph 0.00% 3
telnyx 0.00% 3

Full provider & model leaderboard.

Provider diversity

21 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.

Workspace access

Sign in

Choose a sign in method to access your TrustedRouter workspace.

By signing in you agree to the terms of service and privacy policy.