OpenAI compatible API · Attested · Public status

Alibaba Cloud Model Studio

Explore Alibaba Cloud Model Studio models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.

Verify gateway

Onebase URL to migrate

100sof models and routes

0prompt or output logs. Always.

Alibaba Cloud Model Studioalibaba

No provider claim

All providers

These privacy labels describe Alibaba Cloud Model Studio, the upstream model provider. Confidential requires all three: verified provider compute, end-to-end encryption and explicit zero data retention. Account and billing metadata are outside the content-retention claim.

Provider	Alibaba Cloud Model Studio
API operator country	CN Legal home of the API operator, not an inference-location guarantee.
Headquarters	Not verified
Routing status	Active
Provider website	https://www.alibabacloud.com/
Models	77 public models
Credits routes	77
Zero data retention	not claimed
Verified confidential inference	Not verified
Policy note	No provider-ZDR claim is tracked here. Alibaba Cloud Model Studio model availability and pricing are linked for users who need to review API data handling and regional deployment scope. Policy source

Inference locations

Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.

Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.

Declared countries or regions: Not verified
No inference-location declaration has been verified for this provider.
Can locations change?: Not verified. Do not assume that the serving location is fixed.
Provider region pinning: Not verified.
Pinning through TrustedRouter: No verified provider-specific location pin documented here.
Infrastructure declaration: Inference location not verified; no country-specific residency commitment.
Evidence: Not yet reviewed.

Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.

Measured performance

37 samples

Continuously sampled across Alibaba Cloud Model Studio's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.

p50 TTFT	1894 ms
Effective throughput	70 tok/s n=5
Uptime	100.00%

Model	p50 TTFT	Effective throughput	Uptime	Config excluded	Availability samples
qwen/qwen3.5-flash-2026-02-23	991 ms	—	100.00%	—	2
qwen/qwen3-vl-flash	1206 ms	—	100.00%	—	1
qwen/qwen3.5-122b-a10b	1211 ms	—	100.00%	—	1
qwen/qwen3-235b-a22b	1522 ms	—	100.00%	—	1
qwen/qwen-mt-lite	1589 ms	—	100.00%	—	1
qwen/qwen3-32b	1777 ms	—	100.00%	—	1
qwen/qwen3.7-flash-2026-07-15	1835 ms	—	100.00%	—	1
qwen/qwen3-vl-235b-a22b-thinking	1868 ms	—	100.00%	—	1
qwen/qwen-flash	1894 ms	—	100.00%	—	1
qwen/qwen3.6-35b-a3b	2091 ms	—	100.00%	—	1
qwen/qwen3.7-max	2190 ms	—	100.00%	—	1
deepseek/deepseek-v4-pro	2338 ms	—	100.00%	—	1
qwen/qwen3.5-plus	2727 ms	—	100.00%	—	1
qwen/qwen3-coder-30b-a3b-instruct	2730 ms	—	100.00%	—	1
deepseek/deepseek-v4-flash	2945 ms	140 tok/s n=2	100.00%	—	1
qwen/qwen3.7-max-2026-05-20	2952 ms	—	100.00%	—	1
qwen/qwen3-vl-8b-thinking	3261 ms	—	100.00%	—	1
qwen/qwen-plus-2025-09-11	3300 ms	—	100.00%	—	1
qwen/qwen-vl-ocr-2025-11-20	—	—	100.00%	—	18
moonshotai/kimi-k2.7-code	—	57 tok/s n=2	—	—	0
z-ai/glm-5.2	—	70 tok/s n=1	—	—	0

Alibaba Cloud Model Studio performance history · Full provider & model leaderboard.

Provider models

Models served by Alibaba Cloud Model Studio.

Each row links to pricing, provider, benchmark, and API pages for the model.

Model	AI IQ	Context	Input	Cached input	Output
`alibaba/wan-2.7` Alibaba Wan 2.7	—	5,000	selected route	Not published	selected route
`deepseek/deepseek-v4-flash` DeepSeek: DeepSeek V4 Flash 0423 benchmarks	IQ 122#33	1,048,576	$0.14559/1M	$0.02954/1M	$0.290125/1M
`deepseek/deepseek-v4-flash-0731` DeepSeek: DeepSeek V4 Flash 0731	—	1,048,576	$0.14559/1M	$0.02954/1M	$0.290125/1M
`deepseek/deepseek-v4-pro` DeepSeek: DeepSeek V4 Pro 0423 benchmarks	IQ 123#30	1,048,576	$2.532/1M	$0.2532/1M	$5.064/1M
`moonshotai/kimi-k2.5` MoonshotAI: Kimi K2.5	IQ 110#68	262,144	$0.60557/1M	$0.121325/1M	$3.176605/1M
`moonshotai/kimi-k2.7-code` MoonshotAI: Kimi K2.7 Code benchmarks	IQ 111#66	262,144	$0.94317/1M	$0.1899/1M	$3.917215/1M
`qwen/qwen-flash` Qwen Flash	—	1,048,576	$0.05275/1M	$0.01/1M to $0.026375/1M	$0.422/1M
`qwen/qwen-flash-2025-07-28` Qwen Flash 2025 07 28	—	1,048,576	$0.05275/1M	$0.01/1M to $0.026375/1M	$0.422/1M
`qwen/qwen-mt-flash` Qwen MT Flash	—	131,072	$0.05275/1M	$0.01/1M	$0.422/1M
`qwen/qwen-mt-lite` Qwen MT Lite	—	131,072	$0.05275/1M	$0.01/1M	$0.422/1M
`qwen/qwen-mt-plus` Qwen MT Plus	—	16,384	$0.05275/1M	$0.01/1M	$0.422/1M
`qwen/qwen-mt-turbo` Qwen MT Turbo	—	131,072	$0.05275/1M	$0.01/1M	$0.422/1M
`qwen/qwen-plus` Qwen Plus	—	1,048,576	$0.422/1M	$0.0422/1M to $0.1266/1M	$4.22/1M
`qwen/qwen-plus-2025-07-28` Qwen Plus 2025 07 28	—	1,048,576	$0.422/1M	$0.0422/1M to $0.1266/1M	$4.22/1M
`qwen/qwen-plus-2025-09-11` Qwen Plus 2025 09 11	—	1,048,576	$0.422/1M	$0.0422/1M to $0.1266/1M	$4.22/1M
`qwen/qwen-plus-2025-12-01` Qwen Plus 2025 12 01	—	1,048,576	$0.422/1M	$0.0422/1M to $0.1266/1M	$4.22/1M
`qwen/qwen-plus-character` Qwen Plus Character	—	0	$0.422/1M	$0.0422/1M	$4.22/1M
`qwen/qwen-vl-ocr` Qwen VL OCR	—	262,144	$0.07385/1M	$0.01/1M	$0.1688/1M
`qwen/qwen-vl-ocr-2025-11-20` Qwen VL OCR 2025 11 20	—	262,144	$0.07385/1M	$0.01/1M	$0.1688/1M
`qwen/qwen3-235b-a22b` Qwen3-235B-A22B	—	32,768	$0.7385/1M	$0.07385/1M	$8.862/1M
`qwen/qwen3-235b-a22b-instruct-2507` Qwen3 235B A22B Instruct 2507	—	131,072	$0.24265/1M	$0.024265/1M	$0.9706/1M
`qwen/qwen3-235b-a22b-thinking-2507` Qwen: Qwen3 235B A22B Thinking 2507	—	131,072	$0.24265/1M	$0.024265/1M	$2.4265/1M
`qwen/qwen3-30b-a3b` Qwen: Qwen3 30B A3B	—	40,960	$0.211/1M	$0.0211/1M	$2.532/1M
`qwen/qwen3-30b-a3b-instruct-2507` Qwen: Qwen3 30B A3B Instruct 2507	—	262,144	$0.211/1M	$0.0211/1M	$0.844/1M
`qwen/qwen3-30b-a3b-thinking-2507` Qwen3 30b A3b Thinking 2507	—	262,144	$0.211/1M	$0.0211/1M	$2.532/1M
`qwen/qwen3-32b` Qwen: Qwen3 32B	—	40,960	$0.1688/1M	$0.01688/1M	$0.6752/1M
`qwen/qwen3-8b` Qwen3 8b	—	262,144	$0.1899/1M	$0.01899/1M	$2.2155/1M
`qwen/qwen3-coder-30b-a3b-instruct` Qwen: Qwen3 Coder 30B A3B Instruct	—	160,000	$0.47475/1M	$0.047475/1M to $0.1266/1M	$2.37375/1M
`qwen/qwen3-coder-480b-a35b-instruct` Qwen3 Coder 480B A35B Instruct	—	262,144	$1.5825/1M	$0.15825/1M to $0.47475/1M	$7.9125/1M
`qwen/qwen3-coder-flash` Qwen3 Coder Flash	—	1,048,576	$0.3165/1M	$0.03165/1M to $0.1688/1M	$1.5825/1M
`qwen/qwen3-coder-flash-2025-07-28` Qwen3 Coder Flash 2025 07 28	—	1,048,576	$0.3165/1M	$0.03165/1M to $0.1688/1M	$1.5825/1M
`qwen/qwen3-coder-next` Qwen: Qwen3 Coder Next	—	262,144	$0.3165/1M	$0.03165/1M to $0.1688/1M	$1.5825/1M
`qwen/qwen3-coder-plus` Qwen3 Coder Plus	—	1,048,576	$1.055/1M	$0.1055/1M to $0.633/1M	$5.275/1M
`qwen/qwen3-coder-plus-2025-07-22` Qwen3 Coder Plus 2025 07 22	—	1,048,576	$1.055/1M	$0.1055/1M to $0.633/1M	$5.275/1M
`qwen/qwen3-coder-plus-2025-09-23` Qwen3 Coder Plus 2025 09 23	—	1,048,576	$1.055/1M	$0.1055/1M to $0.633/1M	$5.275/1M
`qwen/qwen3-max` Qwen3 Max	—	262,144	$1.266/1M	$0.1266/1M to $0.3165/1M	$6.33/1M
`qwen/qwen3-max-2025-09-23` Qwen3 Max 2025 09 23	—	262,144	$1.266/1M	$0.1266/1M to $0.3165/1M	$6.33/1M
`qwen/qwen3-max-2026-01-23` Qwen3 Max 2026 01 23	—	262,144	$1.266/1M	$0.1266/1M to $0.3165/1M	$6.33/1M
`qwen/qwen3-max-preview` Qwen3 Max Preview	—	262,144	$1.266/1M	$0.1266/1M to $0.3165/1M	$6.33/1M
`qwen/qwen3-next-80b-a3b-instruct` Qwen: Qwen3 Next 80B A3B Instruct	—	262,144	$0.15825/1M	$0.015825/1M	$1.266/1M
`qwen/qwen3-next-80b-a3b-thinking` Qwen3 Next 80B A3B Thinking	—	262,144	$0.15825/1M	$0.015825/1M	$1.266/1M
`qwen/qwen3-vl-235b-a22b-instruct` Qwen: Qwen3 VL 235B A22B Instruct	—	262,144	$0.7385/1M	$0.07385/1M	$8.862/1M
`qwen/qwen3-vl-235b-a22b-thinking` Qwen: Qwen3 VL 235B A22B Thinking	—	131,072	$0.7385/1M	$0.07385/1M	$8.862/1M
`qwen/qwen3-vl-30b-a3b-instruct` Qwen: Qwen3 VL 30B A3B Instruct	—	262,144	$0.211/1M	$0.0211/1M	$2.532/1M
`qwen/qwen3-vl-30b-a3b-thinking` Qwen: Qwen3 VL 30B A3B Thinking	—	262,144	$0.211/1M	$0.0211/1M	$2.532/1M
`qwen/qwen3-vl-32b-instruct` Qwen3 VL 32b Instruct	—	262,144	$0.211/1M	$0.0211/1M	$2.532/1M
`qwen/qwen3-vl-32b-thinking` Qwen3 VL 32b Thinking	—	262,144	$0.211/1M	$0.0211/1M	$2.532/1M
`qwen/qwen3-vl-8b-instruct` Qwen: Qwen3 VL 8B Instruct	—	262,144	$0.05275/1M	$0.01/1M	$0.422/1M
`qwen/qwen3-vl-8b-thinking` Qwen3-VL-8B-Thinking	—	32,768	$0.05275/1M	$0.01/1M	$0.422/1M
`qwen/qwen3-vl-flash` Qwen3 VL Flash	—	262,144	$0.05275/1M	$0.01/1M to $0.01266/1M	$0.422/1M
`qwen/qwen3-vl-flash-2025-10-15` Qwen3 VL Flash 2025 10 15	—	262,144	$0.05275/1M	$0.01/1M to $0.01266/1M	$0.422/1M
`qwen/qwen3-vl-flash-2026-01-22` Qwen3 VL Flash 2026 01 22	—	262,144	$0.05275/1M	$0.01/1M to $0.01266/1M	$0.422/1M
`qwen/qwen3-vl-plus` Qwen3 VL Plus	—	262,144	$0.211/1M	$0.0211/1M to $0.0633/1M	$1.688/1M
`qwen/qwen3-vl-plus-2025-09-23` Qwen3 VL Plus 2025 09 23	—	262,144	$0.211/1M	$0.0211/1M to $0.0633/1M	$1.688/1M
`qwen/qwen3-vl-plus-2025-12-19` Qwen3 VL Plus 2025 12 19	—	262,144	$0.211/1M	$0.0211/1M to $0.0633/1M	$1.688/1M
`qwen/qwen3.5-122b-a10b` Qwen: Qwen3.5-122B-A10B	—	262,144	$0.422/1M	$0.0422/1M	$3.376/1M
`qwen/qwen3.5-27b` Qwen: Qwen3.5-27B	—	262,144	$0.3165/1M	$0.03165/1M	$2.532/1M
`qwen/qwen3.5-35b-a3b` Qwen: Qwen3.5-35B-A3B	—	262,144	$0.26375/1M	$0.026375/1M	$2.11/1M
`qwen/qwen3.5-397b-a17b` Qwen: Qwen3.5 397B A17B	—	262,144	$0.633/1M	$0.0633/1M	$3.798/1M
`qwen/qwen3.5-flash` Qwen3.5 Flash	—	1,000,000	$0.1055/1M	$0.01055/1M	$0.422/1M
`qwen/qwen3.5-flash-2026-02-23` Qwen3.5 Flash 2026 02 23	—	1,048,576	$0.1055/1M	$0.01055/1M	$0.422/1M
`qwen/qwen3.5-plus` Qwen3.5 Plus	—	1,000,000	$0.422/1M	$0.0422/1M to $0.05275/1M	$2.532/1M
`qwen/qwen3.5-plus-2026-02-15` Qwen3.5 Plus 2026 02 15	—	1,048,576	$0.422/1M	$0.0422/1M to $0.05275/1M	$2.532/1M
`qwen/qwen3.6-35b-a3b` Qwen: Qwen3.6 35B A3B	IQ 101#109	262,144	$0.395625/1M	$0.039563/1M	$2.37375/1M
`qwen/qwen3.6-flash` Qwen3.6 Flash	—	1,048,576	$0.26375/1M	$0.026375/1M to $0.1055/1M	$1.5825/1M
`qwen/qwen3.6-flash-2026-04-16` Qwen3.6 Flash 2026 04 16	—	1,048,576	$0.26375/1M	$0.026375/1M to $0.1055/1M	$1.5825/1M
`qwen/qwen3.6-plus` Qwen3.6 Plus	IQ 110#71	262,144	$0.5275/1M	$0.05275/1M to $0.211/1M	$3.165/1M
`qwen/qwen3.6-plus-2026-04-02` Qwen3.6 Plus 2026-04-02	—	262,144	$0.5275/1M	$0.05275/1M to $0.211/1M	$3.165/1M
`qwen/qwen3.7-flash` Qwen3.7 Flash	IQ #	1,048,576	$0.03165/1M	$0.01/1M to $0.0422/1M	$0.13715/1M
`qwen/qwen3.7-flash-2026-07-15` Qwen3.7 Flash 2026 07 15	—	1,048,576	$0.03165/1M	$0.01/1M to $0.0422/1M	$0.13715/1M
`qwen/qwen3.7-max` Qwen3.7 Max	IQ 119#43	1,000,000	$2.6375/1M	$0.26375/1M	$7.9125/1M
`qwen/qwen3.7-max-2026-05-20` Qwen3.7 Max 2026 05 20	—	1,048,576	$2.6375/1M	$0.26375/1M	$7.9125/1M
`qwen/qwen3.7-max-2026-06-08` Qwen3.7 Max 2026 06 08	—	1,048,576	$2.6375/1M	$0.26375/1M	$7.9125/1M
`qwen/qwen3.7-plus` Qwen3.7 Plus	IQ 112#62	1,000,000	$0.422/1M	$0.0422/1M to $0.1266/1M	$1.688/1M
`qwen/qwen3.7-plus-2026-05-26` Qwen3.7 Plus 2026 05 26	—	1,048,576	$0.422/1M	$0.0422/1M to $0.1266/1M	$1.688/1M
`z-ai/glm-5.1` Z.ai: GLM 5.1 benchmarks	IQ 113#58	202,752	$1.477/1M	$0.2743/1M	$4.642/1M
`z-ai/glm-5.2` Z.ai: GLM 5.2 benchmarks	IQ 119#42	1,048,576	$1.477/1M	$0.2743/1M	$4.642/1M

Questions

Does Alibaba Cloud Model Studio have zero data retention?

TrustedRouter does not currently mark Alibaba Cloud Model Studio as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.

Is Alibaba Cloud Model Studio end-to-end encrypted?

TrustedRouter does not currently mark Alibaba Cloud Model Studio as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.

Which Alibaba Cloud Model Studio models are available through TrustedRouter?

This page currently lists 77 public Alibaba Cloud Model Studio models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.