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
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 | 1908 ms |
|---|---|
| p95 TTFT | 4010 ms |
| Effective throughput | 42 tok/s n=3 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| qwen/qwen3-32b | 1095 ms | — | 100.00% | — | 1 |
| qwen/qwen-mt-flash | 1229 ms | — | 100.00% | — | 1 |
| qwen/qwen-flash | 1458 ms | — | 100.00% | — | 2 |
| qwen/qwen3.7-plus | 1483 ms | — | 100.00% | — | 1 |
| qwen/qwen-plus-2025-12-01 | 1536 ms | — | 100.00% | — | 1 |
| qwen/qwen-plus-2025-07-28 | 1554 ms | — | 100.00% | — | 1 |
| qwen/qwen3-vl-flash | 1613 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-27b | 1735 ms | — | 100.00% | — | 1 |
| qwen/qwen3-coder-flash | 1833 ms | — | 100.00% | — | 2 |
| qwen/qwen-plus | 1885 ms | — | 100.00% | — | 1 |
| qwen/qwen3-8b | 1908 ms | — | 100.00% | — | 1 |
| qwen/qwen3.6-35b-a3b | 1932 ms | — | 100.00% | — | 1 |
| qwen/qwen3.7-plus-2026-05-26 | 1970 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-35b-a3b | 2029 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-122b-a10b | 2094 ms | — | 100.00% | — | 1 |
| qwen/qwen3-vl-8b-instruct | 2136 ms | — | 100.00% | — | 2 |
| deepseek/deepseek-v4-pro | 2603 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash-0731 | 2628 ms | — | 100.00% | — | 1 |
| qwen/qwen-mt-turbo | 3301 ms | — | 100.00% | — | 1 |
| qwen/qwen-vl-ocr-2025-11-20 | 3586 ms | — | 100.00% | — | 1 |
| qwen/qwen3.6-plus-2026-04-02 | 4010 ms | — | 100.00% | — | 1 |
| qwen/qwen-vl-ocr | 5898 ms | — | 100.00% | — | 1 |
| qwen/qwen3.7-flash | — | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash | — | 103 tok/s n=1 | — | — | 0 |
| moonshotai/kimi-k2.7-code | — | 42 tok/s n=1 | — | — | 0 |
| z-ai/glm-5.2 | — | 34 tok/s n=1 | — | — | 0 |