OpenAI compatible API · Attested · Public status

Venice performance

Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Venice.

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

venice

60 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 TTFT1962 ms
p95 TTFT12867 ms
p50 TTFB2495 ms
Effective throughput33 tok/s n=2
Uptime100.00%

Measured model routes

Modelp50 TTFTp50 TTFBEffective throughputUptimeConfig excludedAvailability samples
z-ai/glm-5 993 ms 992 ms 100.00% 2
z-ai/glm-4.7 1363 ms 1363 ms 100.00% 6
qwen/qwen3.6-27b 1442 ms 1442 ms 100.00% 7
z-ai/glm-4.7-flash 1723 ms 1722 ms 100.00% 6
z-ai/glm-4.6 1724 ms 1724 ms 100.00% 4
z-ai/glm-5.1 1962 ms 1962 ms 100.00% 5
z-ai/glm-5-turbo 2481 ms 2480 ms 100.00% 4
qwen/qwen3.5-397b-a17b 2587 ms 2587 ms 100.00% 7
qwen/qwen3.5-9b 3101 ms 3100 ms 100.00% 5
qwen/qwen3-235b-a22b-thinking-2507 3385 ms 3385 ms 100.00% 3
z-ai/glm-5.2 3492 ms 3492 ms 33 tok/s n=2 100.00% 5
z-ai/glm-5v-turbo 4670 ms 4670 ms 100.00% 6
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.