OpenAI compatible API · Attested · Public status
Alibaba Cloud Model Studio performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for Alibaba Cloud Model Studio on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Alibaba Cloud Model Studioalibaba
35 samplesContinuously sampled provider performance. TrustedRouter reports unsupported route and probe-configuration rows separately from provider downtime. Prompt and output content is not stored.
| p50 TTFT | 2201 ms |
|---|---|
| p95 TTFT | 4338 ms |
| Effective throughput | 61 tok/s n=3 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| qwen/qwen3.6-flash | 1444 ms | — | 100.00% | — | 2 |
| qwen/qwen-mt-plus | 1466 ms | — | 100.00% | — | 2 |
| qwen/qwen3.6-flash-2026-04-16 | 1469 ms | — | 100.00% | — | 2 |
| qwen/qwen-plus-character | 1674 ms | — | 100.00% | — | 1 |
| qwen/qwen3-vl-235b-a22b-instruct | 1788 ms | — | 100.00% | — | 1 |
| qwen/qwen3-30b-a3b | 1911 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-plus | 1925 ms | — | 100.00% | — | 1 |
| qwen/qwen3-32b | 1982 ms | — | 100.00% | — | 2 |
| qwen/qwen3.7-flash-2026-07-15 | 1989 ms | — | 100.00% | — | 2 |
| qwen/qwen3.7-max-2026-05-20 | 2015 ms | — | 100.00% | — | 1 |
| qwen/qwen3-235b-a22b-instruct-2507 | 2074 ms | — | 100.00% | — | 1 |
| qwen/qwen3-vl-30b-a3b-instruct | 2116 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.5 | 2201 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash-0731 | 2212 ms | — | 100.00% | — | 2 |
| qwen/qwen3-vl-plus-2025-09-23 | 2247 ms | — | 100.00% | — | 1 |
| qwen/qwen3-coder-plus | 2248 ms | — | 100.00% | — | 1 |
| qwen/qwen3-vl-32b-instruct | 2307 ms | — | 100.00% | — | 2 |
| deepseek/deepseek-v4-pro | 2765 ms | — | 100.00% | — | 1 |
| qwen/qwen3-vl-plus | 2866 ms | — | 100.00% | — | 1 |
| qwen/qwen3-max-2025-09-23 | 3002 ms | — | 100.00% | — | 2 |
| qwen/qwen-flash | 3218 ms | — | 100.00% | — | 1 |
| qwen/qwen3.7-flash | 3422 ms | — | 100.00% | — | 1 |
| qwen/qwen-mt-flash | 3591 ms | — | 100.00% | — | 2 |
| qwen/qwen3.5-flash-2026-02-23 | 3722 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-397b-a17b | 3947 ms | — | 100.00% | — | 1 |
| qwen/qwen3-max | 4338 ms | — | 100.00% | — | 1 |
| qwen/qwen3-235b-a22b-thinking-2507 | — | 61 tok/s n=2 | — | — | 0 |
| z-ai/glm-5.2 | — | 60 tok/s n=1 | — | — | 0 |