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.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
IO Intelligenceio-net
26 samples
Continuously sampled provider performance. TrustedRouter reports unsupported route and probe-configuration rows separately from provider downtime. Prompt and output content is not stored.
| p50 TTFT | 1685 ms |
|---|---|
| p95 TTFT | 3992 ms |
| Effective throughput | 92 tok/s n=11 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| z-ai/glm-5.2 | 1044 ms | 98 tok/s n=1 | 100.00% | — | 2 |
| openai/gpt-oss-120b | 1150 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.7-code | 1189 ms | 176 tok/s n=1 | 100.00% | — | 2 |
| qwen/qwen3-next-80b-a3b-instruct | 1315 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2.6 | 1416 ms | 76 tok/s n=2 | 100.00% | — | 1 |
| z-ai/glm-4.7-flash | 1449 ms | — | 100.00% | — | 1 |
| z-ai/glm-4.6 | 1623 ms | — | 100.00% | — | 2 |
| z-ai/glm-5.3 | 1685 ms | 65 tok/s n=2 | 100.00% | — | 3 |
| intel/qwen3-coder-480b-a35b-instruct-int4-mixed-ar | 1697 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k3 | 1816 ms | 55 tok/s n=1 | 100.00% | — | 3 |
| meta-llama/llama-4-maverick-17b-128e-instruct-fp8 | 1947 ms | — | 100.00% | — | 1 |
| z-ai/glm-4.5-air | 2118 ms | — | 100.00% | — | 1 |
| xiaomi/mimo-v2.5 | 2250 ms | — | 100.00% | — | 1 |
| meta-llama/llama-3.3-70b-instruct | 2403 ms | — | 100.00% | — | 1 |
| qwen/qwen3.8-27b | 2656 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.5 | 2723 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.1 | 3430 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-pro | 5134 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash | — | 92 tok/s n=2 | — | — | 0 |
| google/gemma-4-31b-it | — | 225 tok/s n=2 | — | — | 0 |