Inference provider

Alibaba

49 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.

Models served

Median output speed

57 t/s

Median latency

560ms

Median price / 1M

$0.544

Catalogue

Strongest and fastest on this provider

What the catalogue looks like at the top end, on the two axes that usually decide the choice.

Highest Intelligence Index

Among models this provider serves

Qwen3.8 MaxQwen
58.1
GLM 5.2Z.ai
52.6
V4 Flash 0423DeepSeek
51.8
Qwen3.7 MaxQwen
46.7
V4 ProDeepSeek
45.3
Kimi K2.7 CodeMoonshot AI
43.0
Qwen3.6 Max PreviewQwen
41.1
GLM 5.1Z.ai
41.0
Qwen3.6 PlusQwen
40.5
Qwen3.7 PlusQwen
39.4

View as table

Model	Intelligence
Qwen3.8 Max (Qwen)	58.1
GLM 5.2 (Z.ai)	52.6
V4 Flash 0423 (DeepSeek)	51.8
Qwen3.7 Max (Qwen)	46.7
V4 Pro (DeepSeek)	45.3
Kimi K2.7 Code (Moonshot AI)	43.0
Qwen3.6 Max Preview (Qwen)	41.1
GLM 5.1 (Z.ai)	41.0
Qwen3.6 Plus (Qwen)	40.5
Qwen3.7 Plus (Qwen)	39.4

Fastest output

Median tokens per second

Qwen3 32BQwen
423 t/s
Qwen3 Next 80B A3B ThinkingQwen
242 t/s
Qwen3.5-35B-A3BQwen
203 t/s
Qwen3.5-122B-A10BQwen
145 t/s
GLM 5.2Z.ai
142 t/s
Kimi K2.7 CodeMoonshot AI
140 t/s
Qwen3 30B A3B Thinking 2507Qwen
138 t/s
Qwen3 Coder NextQwen
129 t/s
Qwen3 VL 8B ThinkingQwen
125 t/s
Qwen3 VL 30B A3B ThinkingQwen
117 t/s

View as table

Model	Tokens/s
Qwen3 32B (Qwen)	423
Qwen3 Next 80B A3B Thinking (Qwen)	242
Qwen3.5-35B-A3B (Qwen)	203
Qwen3.5-122B-A10B (Qwen)	145
GLM 5.2 (Z.ai)	142
Kimi K2.7 Code (Moonshot AI)	140
Qwen3 30B A3B Thinking 2507 (Qwen)	138
Qwen3 Coder Next (Qwen)	129
Qwen3 VL 8B Thinking (Qwen)	125
Qwen3 VL 30B A3B Thinking (Qwen)	117

Full catalogue

All 49 models on Alibaba

49 of 49 models


Qwen3.8 Max Qwen	58.1	71.8	58.4	38 t/s	2.9s	$3	$0.58	1M
GLM 5.2 Z.aiopen	52.6	68.8	45.7	142 t/s	712ms	$1.18	$0.23	1.05M
V4 Flash 0423 DeepSeekopen	51.8	69.1	48.4	87 t/s	371ms	$0.11	$0.02	1.05M
Qwen3.7 Max Qwen	46.7	66.0	30.9	47 t/s	1.23s	$2.21	$0.43	1M
V4 Pro DeepSeekopen	45.3	59.4	37.8	71 t/s	380ms	$0.544	$0.09	1.05M
Kimi K2.7 Code Moonshot AIopen	43.0	60.8	30.3	140 t/s	621ms	$1.4	$0.32	262K
Qwen3.6 Max Preview Qwen	41.1	—	—	47 t/s	1.33s	$2.31	$0.54	262K
GLM 5.1 Z.aiopen	41.0	55.8	30.6	67 t/s	289ms	$1.46	$0.29	205K
Qwen3.6 Plus Qwen	40.5	54.5	29.0	39 t/s	982ms	$0.731	$0.17	1M
Qwen3.7 Plus Qwen	39.4	55.9	20.7	12 t/s	872ms	$0.56	$0.12	1M
Qwen3.6 27B Qwenopen	37.7	53.7	27.5	77 t/s	445ms	$1.35	$0.32	262K
Qwen3.5-27B Qwenopen	34.6	—	—	44 t/s	560ms	$0.536	$0.13	262K
Qwen3.5 397B A17B Qwenopen	34.3	48.2	19.8	116 t/s	415ms	$0.877	$0.21	262K
Qwen3.5-122B-A10B Qwenopen	32.8	45.7	21.3	145 t/s	506ms	$0.817	$0.21	262K
Qwen3 Max Thinking Qwen	32.5	—	—	31 t/s	1.14s	$1.56	$0.35	262K
Qwen3.5-35B-A3B Qwenopen	29.9	—	11.8	203 t/s	419ms	$0.355	$0.09	262K
V3.2 DeepSeekopen	25.1	—	—	100 t/s	676ms	$0.302	$0.05	164K
Qwen3 Max Qwen	24.5	—	—	29 t/s	1.04s	$1.56	$0.14	262K
Qwen3 Coder Next Qwenopen	21.3	36.2	8.9	129 t/s	567ms	$0.29	$0.03	262K
Qwen3 VL 235B A22B Instruct Qwenopen	14.4	—	—	32 t/s	715ms	$0.632	$0.06	262K
Qwen3 Next 80B A3B Instruct Qwenopen	13.8	—	—	102 t/s	492ms	$0.343	$0.03	262K
Qwen3 Coder 30B A3B Instruct Qwenopen	13.6	—	—	76 t/s	876ms	$0.12	$0.01	262K
Qwen3 VL 32B Instruct Qwenopen	11.0	—	—	47 t/s	837ms	$0.182	$0.02	131K
Qwen3 VL 30B A3B Instruct Qwenopen	9.9	—	—	16 t/s	417ms	$0.262	$0.02	262K
Qwen3 VL 8B Instruct Qwenopen	8.2	—	—	51 t/s	357ms	$0.202	$0.02	262K
Qwen3.7 Flash Qwen	—	—	—	29 t/s	991ms	$0.055	$0.01	1M
Qwen3.5 Plus 2026-04-20 Qwen	—	—	—	54 t/s	935ms	$0.675	$0.16	1M
Qwen3.6 Flash Qwen	—	—	—	73 t/s	535ms	$0.422	$0.10	1M
Qwen3.5-Flash Qwen	—	—	—	37 t/s	471ms	$0.114	$0.02	1M
Qwen3.5 Plus 2026-02-15 Qwen	—	—	—	66 t/s	1.09s	$0.585	$0.14	1M
Qwen3 VL 8B Thinking Qwenopen	—	—	—	125 t/s	732ms	$0.66	$0.18	131K
Qwen3 VL 30B A3B Thinking Qwenopen	—	—	—	117 t/s	862ms	$0.75	$0.20	262K
Qwen3 VL 235B A22B Thinking Qwenopen	—	—	—	56 t/s	926ms	$1.3	$0.34	131K
Qwen3 Coder Plus Qwen	—	—	—	72 t/s	676ms	$1.3	$0.11	1M
Qwen3 Coder Flash Qwen	—	—	—	23 t/s	1.37s	$0.39	$0.03	1M
Qwen3 Next 80B A3B Thinking Qwenopen	—	—	—	242 t/s	313ms	$0.412	$0.10	262K
Plus 0728 Qwen	—	—	—	29 t/s	531ms	$0.39	$0.03	1M
Plus 0728 (thinking) Qwen	—	—	—	48 t/s	436ms	$0.6	$0.12	1M
Qwen3 30B A3B Thinking 2507 Qwenopen	—	—	—	138 t/s	440ms	$0.75	$0.20	82K
Qwen3 30B A3B Instruct 2507 Qwenopen	—	—	—	57 t/s	323ms	$0.084	$0.007	262K