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
23 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 | 1541 ms |
|---|---|
| p95 TTFT | 2617 ms |
| Effective throughput | 94 tok/s n=8 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| qwen/qwen3.6-27b | 732 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.3 | 1101 ms | 100 tok/s n=1 | 100.00% | — | 1 |
| deepseek/deepseek-r1-0528 | 1298 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.6 | 1404 ms | 72 tok/s n=1 | 100.00% | — | 2 |
| z-ai/glm-5.1 | 1406 ms | — | 100.00% | — | 2 |
| intel/qwen3-coder-480b-a35b-instruct-int4-mixed-ar | 1431 ms | — | 100.00% | — | 2 |
| qwen/qwen3-next-80b-a3b-instruct | 1524 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v3.2 | 1541 ms | — | 100.00% | — | 2 |
| z-ai/glm-5.2 | 1564 ms | 73 tok/s n=1 | 100.00% | — | 2 |
| moonshotai/kimi-k2-instruct-0905 | 1706 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash-0731 | 1794 ms | — | 100.00% | — | 1 |
| meta-llama/llama-4-maverick-17b-128e-instruct-fp8 | 1920 ms | — | 100.00% | — | 1 |
| z-ai/glm-4.6 | 2193 ms | — | 100.00% | — | 1 |
| xiaomi/mimo-v2.6-flash | 2355 ms | — | 100.00% | — | 1 |
| qwen/qwen3.6-35b-a3b | 2444 ms | — | 100.00% | — | 3 |
| qwen/qwen3.8-27b | 2617 ms | — | 100.00% | — | 1 |
| google/gemma-4-31b-it | — | 90 tok/s n=1 | — | — | 0 |
| moonshotai/kimi-k2.7-code | — | 123 tok/s n=2 | — | — | 0 |
| moonshotai/kimi-k3 | — | 94 tok/s n=2 | — | — | 0 |