OpenAI compatible API · Attested · Public status

Google: Gemma 4 31B Performance

TrustedRouter performance signals and provider route posture for Google: Gemma 4 31B.

Verify gateway
Onebase URL to migrate
100sof models and routes
Noneprompt logs by default

google/gemma-4-31b-it

open weights Performance

All models

AI IQ IQ 101 #65 public AI IQ rank for gemma-4-31b
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 Google: Gemma 4 31B — unsupported route and probe-configuration rows are separated from provider downtime, and no prompt or output content is stored.

Providerp50 TTFTp95 TTFTp50 TTFBThroughputUptimeConfig excludedSamples
crusoe 2766 ms 14711 ms 2765 ms 94.12% 17
tinfoil 4039 ms 12474 ms 4038 ms 7 tok/s 95.45% 22
friendli 4206 ms 18467 ms 4206 ms 96.15% 26
cerebras 4744 ms 17932 ms 4743 ms 95.65% 46
deepinfra 4951 ms 7367 ms 4951 ms 0 tok/s 100.00% 4
novita 6502 ms 29219 ms 6501 ms 100.00% 4
lightning 6745 ms 13281 ms 6745 ms 100.00% 16
parasail 7672 ms 9529 ms 7672 ms 100.00% 2
digitalocean 11043 ms 16920 ms 11043 ms 88.89% 9
siliconflow 12465 ms 24203 ms 12465 ms 100.00% 7

Full provider & model leaderboard.

Provider diversity

23 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. New email and OAuth accounts include $0.10 in starter credit; wallet-only accounts start at $0.

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