Inference provider

Alibaba: AI models and API pricing

Every tracked model Alibaba serves through OpenRouter, with Alibaba's own input and output price per 1M tokens, the context window it serves, disclosed quantization and measured endpoint uptime. Rows link to the model page, where every provider's deployment is listed side by side.

Snapshot as of 1 October 2026

Alibaba serves 57 tracked models through 59 endpoints as of 1 October 2026; the highest-ranked is Qwen3.8 Max (0902) (ModelCap Index #7); mean measured uptime is 97.81%.

Models served

On the ModelCap Index

Cheapest output price

$0.13/1M

Language models on Alibaba (57)

Ranked models first, in ModelCap Index order. Prices are the lowest Alibaba lists for the model; the endpoint count shows how many deployments carry it.

Language models served by Alibaba, with price, context, quantization and uptime
#	Model	ModelCap Index	Input $/1M	Output $/1M	Context	Quantization	Uptime (30 min)	Endpoints
1	Qwen3.8 Max (0902)Qwen	#783.0	$2.00	$6.00	1M	—	99.57%	1
2	Kimi K3Moonshot AI	#1082.2	$3.45	$17.25	1M	—	100.0%	1
3	GLM 5.3Z.ai	#1180.9	$1.19	$3.74	1M	—	100.0%	2
4	DeepSeek V4.1 FlashDeepSeek	#1579.3	$0.15	$0.60	1M	—	97.57%	1Open weights
5	Qwen3.8 FlashQwen	#1878.4	$0.15	$0.47	1M	—	99.73%	1
6	DeepSeek V4 Pro 0813DeepSeek	#2476.4	$0.581	$1.74	1M	—	99.29%	1Open weights
7	Qwen3.7 PlusQwen	#3071.9	$0.32	$1.28	1M	—	99.84%	1
8	Qwen3.8 27BQwen	#3968.9	$0.425	$2.55	1M	—	99.73%	1Open weights
9	Qwen3.5 397B A17BQwen	#4368.0	$0.39	$2.34	262K	—	100.0%	1Open weights
10	Kimi K2.7 CodeMoonshot AI	#4965.9	$0.95	$4.00	262K	fp8	—	1
11	Qwen3 235B A22B Instruct 2507Qwen	#6462.1	$0.15	$0.598	131K	—	99.77%	1Open weights
12	DeepSeek V3.2DeepSeek	#6661.7	$0.37	$1.11	131K	fp8	86.85%	1Open weights
13	Qwen3.5-122B-A10BQwen	#7759.5	$0.26	$2.08	262K	—	99.66%	1Open weights
14	Qwen3 VL 235B A22B InstructQwen	#7859.5	$0.26	$1.04	131K	—	98.87%	1Open weights
15	Qwen3 235B A22BQwen	#9255.7	$0.455	$1.82	131K	—	89.79%	1Open weights
16	Qwen3 235B A22B Thinking 2507Qwen	#9654.8	$0.23	$2.30	131K	—	99.84%	1Open weights
17	Qwen3 Next 80B A3B InstructQwen	#9854.7	$0.098	$0.78	131K	—	99.86%	1Open weights
18	Qwen3 Coder 30B A3B InstructQwen	#9954.1	$0.292	$1.46	262K	—	—	1Open weights
19	Qwen3 VL 235B A22B ThinkingQwen	#10153.8	$0.40	$4.00	131K	—	—	1Open weights
20	Qwen3 Coder NextQwen	#11053.3	$0.30	$1.50	262K	—	99.57%	1Open weights
21	Qwen3 Coder 480B A35BQwen	#11551.9	$0.975	$4.88	262K	—	—	1Open weights
22	Qwen3 30B A3B Instruct 2507Qwen	#12050.6	$0.13	$0.52	131K	—	99.93%	1Open weights
23	Qwen3 Next 80B A3B ThinkingQwen	#12746.9	$0.15	$1.20	131K	—	—	1Open weights
24	Qwen3 30B A3BQwen	#17135.7	$0.13	$0.52	131K	—	99.80%	1Open weights
25	GLM 5.3 PrimeZ.ai	—	$2.80	$8.80	1M	—	99.84%	1
26	Qwen3 14BQwen	—	$0.227	$0.91	131K	—	100.0%	1Open weights
27	Qwen3 30B A3B Thinking 2507Qwen	—	$0.20	$2.40	82K	—	—	1Open weights
28	Qwen3 8BQwen	—	$0.117	$0.455	131K	—	99.93%	1Open weights
29	Qwen3 Coder FlashQwen	—	$0.195	$0.975	1M	—	100.0%	1
30	Qwen3 Max ThinkingQwen	—	$0.78	$3.90	262K	—	—	1
31	Qwen3 VL 30B A3B InstructQwen	—	$0.13	$0.52	131K	—	99.71%	1Open weights
32	Qwen3 VL 30B A3B ThinkingQwen	—	$0.20	$2.40	131K	—	—	1Open weights
33	Qwen3 VL 32B InstructQwen	—	$0.104	$0.416	131K	—	100.0%	1Open weights
34	Qwen3 VL 8B InstructQwen	—	$0.117	$0.455	131K	—	99.58%	1Open weights
35	Qwen3 VL 8B ThinkingQwen	—	$0.18	$2.10	131K	—	—	1Open weights
36	Qwen3.8 Max PrimeQwen	—	$4.00	$12.00	1M	—	98.51%	1
37	Qwen3.8 Omni FlashQwen	—	$0.15	$0.47	1M	—	99.08%	1
38	DeepSeek V4 Flash 0423DeepSeek	—	$0.134	$0.268	1M	fp8	98.88%	1Open weights
39	DeepSeek V4 Flash 0731DeepSeek	—	$0.176	$0.528	1M	—	98.78%	1Open weights
40	DeepSeek V4 Pro 0423DeepSeek	—	$1.42	$2.83	1M	fp8	43.29%	1Open weights
41	GLM 5.1Z.ai	—	$1.33	$4.18	203K	fp8	—	1Open weights
42	GLM 5.2Z.ai	—	$0.966	$3.04	1M	fp8	100.0%	2Open weights
43	Qwen Plus 0728Qwen	—	$0.26	$0.78	1M	—	—	1
44	Qwen-PlusQwen	—	$0.26	$0.78	1M	—	—	1
45	Qwen3 MaxQwen	—	$0.78	$3.90	262K	—	99.91%	1
46	Qwen3.5 Plus 2026-02-15Qwen	—	$0.26	$1.56	1M	—	99.67%	1
47	Qwen3.5 Plus 2026-04-20Qwen	—	$0.30	$1.80	1M	—	100.0%	1
48	Qwen3.5-27BQwen	—	$0.195	$1.56	262K	—	99.71%	1Open weights
49	Qwen3.5-35B-A3BQwen	—	$0.163	$1.30	262K	—	98.51%	1Open weights
50	Qwen3.5-FlashQwen	—	$0.065	$0.26	1M	—	99.82%	1
51	Qwen3.6 27BQwen	—	$0.45	$2.70	262K	—	99.47%	1Open weights
52	Qwen3.6 FlashQwen	—	$0.188	$1.13	1M	—	99.64%	1
53	Qwen3.6 Max PreviewQwen	—	$1.03	$6.16	262K	—	—	1
54	Qwen3.6 PlusQwen	—	$0.325	$1.95	1M	—	100.0%	1
55	Qwen3.7 FlashQwen	—	$0.03	$0.13	1M	—	100.0%	1
56	Qwen3.7 MaxQwen	—	$1.48	$4.42	1M	—	100.0%	1
57	Qwen3.8 Max (0803)Qwen	—	$2.00	$6.00	1M	—	99.57%	1

Alibaba on ModelCap: common questions

How many AI models does Alibaba serve?

57 tracked models as of 1 October 2026: 57 language models (24 with a public ModelCap Index position), across 59 live endpoints observed through OpenRouter.

What is the best model available on Alibaba?

Qwen3.8 Max (0902) from Qwen is the highest-ranked language model Alibaba serves, at ModelCap Index position #7 and $6.00 per 1M output tokens on Alibaba. The table lists every model in Index order.

What is the cheapest model on Alibaba?

Qwen3.7 Flash at $0.13 per 1M output tokens ($0.03 per 1M input), the lowest positive language-token price Alibaba lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.

Which Alibaba model has the largest context window?

Kimi K3, served with a 1M-token context window on Alibaba. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.

How reliable is Alibaba?

Mean measured uptime across Alibaba endpoints is 97.81% over the last 30 minutes, as reported by OpenRouter at the time of the snapshot. Per-model uptime is in the table; it is a live operational signal, not a service-level guarantee.

Where do the Alibaba prices come from?

From the OpenRouter catalogue entry for each Alibaba endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where Alibaba exposes several deployments of one model at different prices, the table shows the lowest and notes the count; the model page lists each deployment.

How current is this page?

This page uses the published ModelCap snapshot dated 1 October 2026. Publication and page updates happen separately. Offers retained from a failed refresh are marked stale in the data and are not counted here.