OpenAI compatible API · Attested · Public status
Alibaba Cloud Model Studio performance
Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Alibaba Cloud Model Studio.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
alibaba
49 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 | 2274 ms |
|---|---|
| p95 TTFT | 4123 ms |
| p50 TTFB | 2454 ms |
| Effective throughput | 37 tok/s n=8 |
| Uptime | 93.88% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| qwen/qwen3-vl-30b-a3b-instruct | 1139 ms | 1139 ms | — | 100.00% | — | 1 |
| qwen/qwen3-vl-flash-2025-10-15 | 1185 ms | 1185 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-27b | 1341 ms | 1341 ms | — | 100.00% | — | 2 |
| qwen/qwen-plus-2025-12-01 | 1351 ms | 1351 ms | — | 100.00% | — | 2 |
| qwen/qwen3.7-flash-2026-07-15 | 1387 ms | 1386 ms | 123 tok/s n=1 | 100.00% | — | 1 |
| qwen/qwen3-30b-a3b-instruct-2507 | 1446 ms | 1446 ms | — | 100.00% | — | 1 |
| qwen/qwen3-vl-flash | 1452 ms | 1452 ms | — | 100.00% | — | 2 |
| qwen/qwen3-max | 1519 ms | 1519 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-35b-a3b | 1815 ms | 1815 ms | — | 100.00% | — | 1 |
| qwen/qwen-vl-ocr | 2022 ms | 2021 ms | — | 100.00% | — | 1 |
| qwen/qwen3-vl-plus-2025-09-23 | 2085 ms | 2085 ms | — | 100.00% | — | 2 |
| qwen/qwen-mt-flash | 2087 ms | 2087 ms | — | 100.00% | — | 1 |
| qwen/qwen3-vl-8b-thinking | 2159 ms | 2159 ms | — | 100.00% | — | 2 |
| qwen/qwen3.7-max-2026-06-08 | 2162 ms | 2162 ms | — | 100.00% | — | 1 |
| qwen/qwen3-max-preview | 2197 ms | 2197 ms | — | 100.00% | — | 1 |
| qwen/qwen3.6-plus | 2253 ms | 2253 ms | — | 100.00% | — | 2 |
| qwen/qwen3-next-80b-a3b-instruct | 2274 ms | 2274 ms | — | 100.00% | — | 1 |
| qwen/qwen3.6-35b-a3b | 2392 ms | 2392 ms | — | 100.00% | — | 1 |
| qwen/qwen3-vl-32b-thinking | 2430 ms | 2429 ms | — | 100.00% | — | 2 |
| qwen/qwen3-vl-235b-a22b-thinking | 2454 ms | 2454 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-plus | 2484 ms | 2484 ms | — | 100.00% | — | 2 |
| qwen/qwen3-coder-plus-2025-07-22 | 2494 ms | 2494 ms | — | 100.00% | — | 1 |
| qwen/qwen3-next-80b-a3b-thinking | 2640 ms | 2640 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2.5 | 2959 ms | 2959 ms | — | 100.00% | — | 1 |
| qwen/qwen3.6-flash | 3051 ms | 3051 ms | — | 100.00% | — | 1 |
| qwen/qwen3-235b-a22b-instruct-2507 | 3299 ms | 3299 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash | 3404 ms | 3404 ms | 82 tok/s n=1 | 100.00% | — | 1 |
| moonshotai/kimi-k2.7-code | 3421 ms | 3421 ms | — | 100.00% | — | 1 |
| qwen/qwen-plus-2025-09-11 | 3520 ms | 3520 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-plus-2026-02-15 | 3561 ms | 3560 ms | — | 100.00% | — | 3 |
| qwen/qwen3.7-plus | 3597 ms | 3596 ms | — | 100.00% | — | 1 |
| qwen/qwen3-coder-flash | 3776 ms | 3775 ms | — | 100.00% | — | 1 |
| qwen/qwen3.7-max | 4036 ms | 4036 ms | — | 100.00% | — | 2 |
| qwen/qwen3.7-plus-2026-05-26 | 11343 ms | 11343 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-pro | — | — | 36 tok/s n=2 | — | — | 0 |
| qwen/qwen-plus-character | — | — | 33 tok/s n=1 | — | — | 0 |
| qwen/qwen3-vl-flash-2026-01-22 | — | — | — | 0.00% | — | 3 |
| qwen/qwen3.7-flash | — | — | 114 tok/s n=1 | — | — | 0 |
| z-ai/glm-5.2 | — | — | 37 tok/s n=2 | — | — | 0 |