OpenAI compatible API · Attested · Public status

Alibaba Cloud Model Studio performance

Name: Alibaba Cloud Model Studio TrustedRouter performance measurements
Creator: TrustedRouter
License: https://www.apache.org/licenses/LICENSE-2.0

Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Alibaba Cloud Model Studio.

Verify gateway

Onebase URL to migrate

100sof models and routes

0prompt or output logs. Always.

`alibaba`

209 samples

Provider overview

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	—
p95 TTFT	—
p50 TTFB	—
Effective throughput	—
Uptime	0.00%

Measured model routes

Model	p50 TTFT	p50 TTFB	Effective throughput	Uptime	Config excluded	Availability samples
deepseek/deepseek-v4-flash	—	—	—	0.00%	—	2
deepseek/deepseek-v4-pro	—	—	—	0.00%	—	5
moonshotai/kimi-k2.5	—	—	—	0.00%	—	3
moonshotai/kimi-k2.7-code	—	—	—	0.00%	—	4
qwen/qwen-flash	—	—	—	0.00%	—	2
qwen/qwen-flash-2025-07-28	—	—	—	0.00%	—	3
qwen/qwen-mt-flash	—	—	—	0.00%	—	2
qwen/qwen-mt-lite	—	—	—	0.00%	—	2
qwen/qwen-mt-plus	—	—	—	0.00%	—	2
qwen/qwen-mt-turbo	—	—	—	0.00%	—	2
qwen/qwen-plus	—	—	—	0.00%	—	5
qwen/qwen-plus-2025-07-28	—	—	—	0.00%	—	8
qwen/qwen-plus-2025-09-11	—	—	—	0.00%	—	3
qwen/qwen-plus-2025-12-01	—	—	—	0.00%	—	1
qwen/qwen-plus-character	—	—	—	0.00%	—	2
qwen/qwen-vl-ocr	—	—	—	0.00%	—	4
qwen/qwen-vl-ocr-2025-11-20	—	—	—	0.00%	—	3
qwen/qwen3-235b-a22b	—	—	—	0.00%	—	3
qwen/qwen3-235b-a22b-instruct-2507	—	—	—	0.00%	—	4
qwen/qwen3-235b-a22b-thinking-2507	—	—	—	0.00%	—	2
qwen/qwen3-30b-a3b	—	—	—	0.00%	—	6
qwen/qwen3-30b-a3b-thinking-2507	—	—	—	0.00%	—	2
qwen/qwen3-32b	—	—	—	0.00%	—	1
qwen/qwen3-8b	—	—	—	0.00%	—	4
qwen/qwen3-coder-30b-a3b-instruct	—	—	—	0.00%	—	1
qwen/qwen3-coder-480b-a35b-instruct	—	—	—	0.00%	—	2
qwen/qwen3-coder-flash	—	—	—	0.00%	—	3
qwen/qwen3-coder-flash-2025-07-28	—	—	—	0.00%	—	3
qwen/qwen3-coder-next	—	—	—	0.00%	—	2
qwen/qwen3-coder-plus	—	—	—	0.00%	—	1
qwen/qwen3-coder-plus-2025-07-22	—	—	—	0.00%	—	3
qwen/qwen3-coder-plus-2025-09-23	—	—	—	0.00%	—	5
qwen/qwen3-max	—	—	—	0.00%	—	2
qwen/qwen3-max-2025-09-23	—	—	—	0.00%	—	3
qwen/qwen3-max-2026-01-23	—	—	—	0.00%	—	3
qwen/qwen3-next-80b-a3b-instruct	—	—	—	0.00%	—	4
qwen/qwen3-next-80b-a3b-thinking	—	—	—	0.00%	—	2
qwen/qwen3-vl-235b-a22b-instruct	—	—	—	0.00%	—	3
qwen/qwen3-vl-235b-a22b-thinking	—	—	—	0.00%	—	3
qwen/qwen3-vl-30b-a3b-instruct	—	—	—	0.00%	—	3
qwen/qwen3-vl-30b-a3b-thinking	—	—	—	0.00%	—	4
qwen/qwen3-vl-32b-instruct	—	—	—	0.00%	—	2
qwen/qwen3-vl-32b-thinking	—	—	—	0.00%	—	2
qwen/qwen3-vl-8b-instruct	—	—	—	0.00%	—	3
qwen/qwen3-vl-8b-thinking	—	—	—	0.00%	—	4
qwen/qwen3-vl-flash	—	—	—	0.00%	—	2
qwen/qwen3-vl-flash-2025-10-15	—	—	—	0.00%	—	5
qwen/qwen3-vl-flash-2026-01-22	—	—	—	0.00%	—	4
qwen/qwen3-vl-plus	—	—	—	0.00%	—	1
qwen/qwen3-vl-plus-2025-12-19	—	—	—	0.00%	—	2
qwen/qwen3.5-122b-a10b	—	—	—	0.00%	—	2
qwen/qwen3.5-27b	—	—	—	0.00%	—	2
qwen/qwen3.5-flash	—	—	—	0.00%	—	3
qwen/qwen3.5-flash-2026-02-23	—	—	—	0.00%	—	5
qwen/qwen3.5-plus	—	—	—	0.00%	—	1
qwen/qwen3.5-plus-2026-02-15	—	—	—	0.00%	—	4
qwen/qwen3.6-35b-a3b	—	—	—	0.00%	—	4
qwen/qwen3.6-flash	—	—	—	0.00%	—	3
qwen/qwen3.6-flash-2026-04-16	—	—	—	0.00%	—	2
qwen/qwen3.6-plus	—	—	—	0.00%	—	2
qwen/qwen3.6-plus-2026-04-02	—	—	—	0.00%	—	4
qwen/qwen3.7-flash	—	—	—	0.00%	—	5
qwen/qwen3.7-flash-2026-07-15	—	—	—	0.00%	—	1
qwen/qwen3.7-max	—	—	—	0.00%	—	2
qwen/qwen3.7-max-2026-06-08	—	—	—	0.00%	—	5
qwen/qwen3.7-plus	—	—	—	0.00%	—	5
qwen/qwen3.7-plus-2026-05-26	—	—	—	0.00%	—	1
z-ai/glm-5.1	—	—	—	0.00%	—	2
z-ai/glm-5.2	—	—	—	0.00%	—	9