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 11 August 2026

Alibaba serves 44 tracked models through 45 endpoints as of 11 August 2026; the highest-ranked is Qwen3.8 Max (ModelCap Index #5); mean measured uptime is 97.05%.

Models served

On the ModelCap Index

Cheapest output price

$0.13/1M

Language models on Alibaba (44)

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 MaxQwen	#578.4	$2.00	$6.00	1M	—	100.0%	1
2	GLM 5.2Z.ai	#1370.5	$0.966	$3.04	1M	fp8	99.88%	2Open weights
3	Qwen3.7 PlusQwen	#1666.4	$0.32	$1.28	1M	fp8	100.0%	1
4	Qwen3.5 397B A17BQwen	#2261.6	$0.39	$2.34	262K	fp8	100.0%	1Open weights
5	Qwen3 235B A22B Instruct 2507Qwen	#3153.6	$0.15	$0.598	131K	fp8	100.0%	1Open weights
6	Qwen3.6 27BQwen	#3251.9	$0.45	$2.70	262K	fp8	100.0%	1Open weights
7	Qwen3.5-122B-A10BQwen	#3351.8	$0.26	$2.08	262K	fp8	99.93%	1Open weights
8	Qwen3 VL 235B A22B InstructQwen	#3451.5	$0.26	$1.04	131K	fp8	100.0%	1Open weights
9	Qwen3 Next 80B A3B InstructQwen	#4046.6	$0.098	$0.78	131K	fp8	100.0%	1Open weights
10	Qwen3 VL 235B A22B ThinkingQwen	#4245.4	$0.40	$4.00	131K	fp8	—	1Open weights
11	Qwen3 235B A22B Thinking 2507Qwen	#4345.3	$0.23	$2.30	131K	fp8	100.0%	1Open weights
12	Qwen3 Coder 480B A35BQwen	#4643.7	$0.975	$4.88	262K	fp8	—	1Open weights
13	Qwen3 30B A3B Instruct 2507Qwen	#4841.6	$0.13	$0.52	131K	fp8	100.0%	1Open weights
14	Qwen3 235B A22BQwen	#5139.2	$0.455	$1.82	131K	fp8	100.0%	1Open weights
15	Qwen3 Max ThinkingQwen	#5238.6	$0.78	$3.90	262K	fp8	—	1
16	Qwen3 Next 80B A3B ThinkingQwen	#5936.7	$0.15	$1.20	131K	fp8	—	1Open weights
17	Qwen3 32BQwen	#7229.2	$0.104	$0.416	131K	fp8	0.00%	1Open weights
18	Qwen3 Coder 30B A3B InstructQwen	#7428.4	$0.292	$1.46	262K	fp8	—	1Open weights
19	Qwen3 14BQwen	#8725.7	$0.227	$0.91	131K	fp8	100.0%	1Open weights
20	Qwen3 8BQwen	#8825.7	$0.117	$0.455	131K	fp8	100.0%	1Open weights
21	Qwen3 Coder FlashQwen	#8925.7	$0.195	$0.975	1M	fp8	100.0%	1
22	Qwen3 VL 30B A3B ThinkingQwen	#9025.7	$0.20	$2.40	131K	fp8	—	1Open weights
23	Qwen3 VL 8B ThinkingQwen	#9125.7	$0.18	$2.10	131K	fp8	—	1Open weights
24	Qwen3.7 FlashQwen	#9225.7	$0.03	$0.13	1M	—	100.0%	1
25	Qwen3 30B A3BQwen	#18024.3	$0.13	$0.52	131K	fp8	100.0%	1Open weights
26	Kimi K2.7 CodeMoonshot AI	#18921.5	$0.95	$4.00	262K	fp8	100.0%	1
27	Qwen3 Coder NextQwen	#19021.2	$0.30	$1.50	262K	—	100.0%	1Open weights
28	Qwen3 VL 8B InstructQwen	#2108.8	$0.117	$0.455	131K	fp8	99.91%	1Open weights
29	Qwen3 VL 32B InstructQwen	#2146.7	$0.104	$0.416	131K	fp8	100.0%	1Open weights
30	Qwen3 VL 30B A3B InstructQwen	#2184.1	$0.13	$0.52	131K	fp8	100.0%	1Open weights
31	Qwen3 30B A3B Thinking 2507Qwen	—	$0.20	$2.40	82K	fp8	—	1Open weights
32	GLM 5.1Z.ai	—	$1.33	$4.18	203K	fp8	100.0%	1Open weights
33	Qwen Plus 0728Qwen	—	$0.26	$0.78	1M	fp8	—	1
34	Qwen-PlusQwen	—	$0.26	$0.78	1M	fp8	100.0%	1
35	Qwen3 MaxQwen	—	$0.78	$3.90	262K	fp8	100.0%	1
36	Qwen3.5 Plus 2026-02-15Qwen	—	$0.26	$1.56	1M	fp8	100.0%	1
37	Qwen3.5 Plus 2026-04-20Qwen	—	$0.30	$1.80	1M	fp8	100.0%	1
38	Qwen3.5-27BQwen	—	$0.195	$1.56	262K	fp8	100.0%	1Open weights
39	Qwen3.5-35B-A3BQwen	—	$0.163	$1.30	262K	fp8	—	1Open weights
40	Qwen3.5-FlashQwen	—	$0.065	$0.26	1M	fp8	100.0%	1
41	Qwen3.6 FlashQwen	—	$0.188	$1.13	1M	fp8	100.0%	1
42	Qwen3.6 Max PreviewQwen	—	$1.03	$6.16	262K	fp8	—	1
43	Qwen3.6 PlusQwen	—	$0.325	$1.95	1M	fp8	100.0%	1
44	Qwen3.7 MaxQwen	—	$1.48	$4.42	1M	fp8	100.0%	1

Alibaba on ModelCap: common questions

How many AI models does Alibaba serve?

44 tracked models as of 11 August 2026: 44 language models (30 with a public ModelCap Index position), across 45 live endpoints observed through OpenRouter.

What is the best model available on Alibaba?

Qwen3.8 Max from Qwen is the highest-ranked language model Alibaba serves, at ModelCap Index position #5 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?

GLM 5.2, 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 97.05% 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?

It re-renders within a minute of every dataset refresh; this snapshot was published 11 August 2026. Offers retained from a failed refresh are marked stale in the data and are not counted here.