OpenAI compatible API · Attested · Public status

IO Intelligence performance

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

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

IO Intelligenceio-net

24 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 TTFT2023 ms
p95 TTFT3863 ms
Effective throughput140 tok/s n=7
Uptime100.00%

Measured model routes

Modelp50 TTFTEffective throughputUptimeConfig excludedAvailability samples
deepseek/deepseek-v3.2 941 ms 100.00% 1
z-ai/glm-4.7-flash 1311 ms 100.00% 1
moonshotai/kimi-k2.7-code 1401 ms 100.00% 1
moonshotai/kimi-k2.5 1468 ms 100.00% 1
mistralai/mistral-nemo-instruct-2407 1480 ms 100.00% 2
deepseek/deepseek-v4-flash-0731 1512 ms 100.00% 1
openai/gpt-oss-20b 1537 ms 100.00% 1
z-ai/glm-5.1 1547 ms 100.00% 1
z-ai/glm-5.2 1668 ms 122 tok/s n=1 100.00% 1
openai/gpt-oss-120b 1851 ms 140 tok/s n=2 100.00% 1
z-ai/glm-4.7 2023 ms 100.00% 1
moonshotai/kimi-k3 2147 ms 150 tok/s n=2 100.00% 1
qwen/qwen3.6-27b 2936 ms 100.00% 1
meta-llama/llama-4-maverick-17b-128e-instruct-fp8 3065 ms 100.00% 1
meta-llama/llama-3.3-70b-instruct 3224 ms 100.00% 1
qwen/qwen3.6-35b-a3b 3346 ms 100.00% 3
moonshotai/kimi-k2-instruct-0905 3485 ms 100.00% 1
z-ai/glm-5.3 3523 ms 100.00% 1
deepseek/deepseek-v4-pro 3794 ms 100.00% 1
z-ai/glm-4.5-air 3863 ms 100.00% 1
z-ai/glm-5.3-flash 8004 ms 100.00% 1
deepseek/deepseek-v4-flash 67 tok/s n=1 0
moonshotai/kimi-k2.6 47 tok/s n=1 0
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.