Find a model

Browse the full catalog →

OpenAI compatible API · Attested · Public status

Greenference performance

Review measured TTFT, effective throughput, uptime, and sampled model routes for Greenference on TrustedRouter using metadata-only production probes.

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

Greenferencegreenference

21 samples

Provider overview

Continuously sampled provider performance. TrustedRouter reports unsupported route and probe-configuration rows separately from provider downtime. Prompt and output content is not stored.

p50 TTFT1430 ms
p95 TTFT2991 ms
Effective throughput90 tok/s n=1
Uptime100.00%

Measured model routes

Modelp50 TTFTEffective throughputUptimeConfig excludedAvailability samples
qwen/qwen3-8b 821 ms — 100.00% — 1
qwen/qwen3-14b 941 ms — 100.00% — 3
z-ai/glm-4.7-flash 977 ms — 100.00% — 1
openai/gpt-oss-20b 1125 ms — 100.00% — 1
qwen/qwen3.6-27b 1155 ms — 100.00% — 2
z-ai/glm-5.3-flash 1430 ms — 100.00% — 3
qwen/qwen3.5-9b 1627 ms — 100.00% — 5
qwen/qwen3-30b-a3b 2563 ms — 100.00% — 2
qwen/qwen3-32b 2644 ms — 100.00% — 3
google/gemma-4-31b-it — 90 tok/s n=1 — — 0
Workspace access

Sign in

Choose a sign in method to access your TrustedRouter workspace.

New to TrustedRouter?

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