OpenAI compatible API. Attested gateway. Public status.

Google: Gemma 4 31B Performance

Name: Google: Gemma 4 31B TrustedRouter performance measurements
Creator: TrustedRouter
License: https://www.apache.org/licenses/LICENSE-2.0

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

Verify gateway

1 URLbase_url migration

100smodels and routes

0prompt logs by default

`google/gemma-4-31b-it`

open weights Performance

All models

AI IQ IQ 98 #59 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.

Provider	p50 TTFT	p95 TTFT	p50 TTFB	Throughput	Uptime	Config excluded	Samples
novita	1423 ms	11693 ms	1423 ms	—	100.00%	—	2
lightning	4111 ms	14805 ms	4111 ms	—	100.00%	—	250
deepinfra	5082 ms	18168 ms	5082 ms	—	100.00%	—	29
tinfoil	6050 ms	21456 ms	6050 ms	—	94.34%	—	53
crusoe	7088 ms	20099 ms	7088 ms	—	100.00%	—	12
parasail	13852 ms	18886 ms	13852 ms	—	100.00%	—	5

Full provider & model leaderboard.

Provider diversity

14 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.