OpenAI compatible API · Attested · Public status

MiniMax: MiniMax M3 Performance

Compare measured TTFT, throughput, uptime, and route health for MiniMax: MiniMax M3 across TrustedRouter providers using metadata-only production probes.

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 115 #45 public AI IQ rank for minimax-m3
View AI IQ profile

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.

Providerp50 TTFTp95 TTFTEffective throughputUptimeConfig excludedAvailability samples
together 1434 ms 1599 ms 40 tok/s n=1 100.00% 37
fireworks 1979 ms 3499 ms 150 tok/s n=1 100.00% 17
telnyx 1170 ms 3580 ms 132 tok/s n=1 100.00% 4
parasail 1617 ms 4837 ms 156 tok/s n=1 100.00% 4
minimax 2010 ms 4126 ms 153 tok/s n=2 100.00% 6
featherless 3316 ms 3316 ms 122 tok/s n=1 100.00% 1
morph 10027 ms 25067 ms 97 tok/s n=1 40.00% 5
atlas-cloud 75 tok/s n=1 0
deepinfra 28 tok/s n=1 0
novita 102 tok/s n=1 0
wandb 74 tok/s n=1 0

Full provider & model leaderboard.

Provider diversity

12 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.