Skip to content
ModelCap

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. Models with a position on a ModelCap board link to their model page, where every provider's deployment is listed side by side.

Snapshot as of 19 November 2026

Alibaba serves 34 tracked models through 44 endpoints as of 19 November 2026; the highest-ranked is Kimi K3.1 Pro (ModelCap Index #11); mean measured uptime is 96.34%.

Models served
34
On the ModelCap Index
13
Cheapest output price
$0.13/1M

Language models on Alibaba (34)

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
#ModelModelCap IndexInput $/1MOutput $/1MContextQuantizationUptime (30 min)Endpoints
1Kimi K3.1 ProMoonshot AI#1180.0$2.00$10.001M—100.0%1
2GLM 5.3 PrimeZ.ai#1279.7$1.68$5.281M—100.0%1
3Qwen3.8 Max PrimeQwen#1379.5$4.00$12.001M—100.0%1
4Kimi K3Moonshot AI#1779.0$3.00$15.001M—100.0%1
5GLM 5.3Z.ai#1978.5$1.19$3.741M—100.0%2
6DeepSeek V4 Pro 0813DeepSeek#3473.0$1.12$3.371M—100.0%2Open weights
7Qwen4 MaxQwen#3672.8$1.42$4.271M—100.0%1
8Qwen3.7 PlusQwen#4370.6$0.32$1.281M—100.0%2
9Qwen3.5 397B A17BQwen#5267.2$0.39$2.34262K—100.0%1Open weights
10Qwen3.8 27BQwen#6863.1$0.425$2.551M—100.0%1Open weights
11DeepSeek V4.1 Flash 1017DeepSeek#9258.5$0.18$0.721M—100.0%1Open weights
12Qwen3.5-122B-A10BQwen#9956.7$0.26$2.08262K—100.0%1Open weights
13Qwen3.8 FlashQwen#10556.1$0.15$0.471M—100.0%2
14Kimi K2.7 CodeMoonshot AI—$0.95$4.00262Kfp8—1
15Qwen3 Coder FlashQwen—$0.195$0.9751M—100.0%1
16Qwen3.8 Omni FlashQwen—$0.15$0.471M—100.0%1
17DeepSeek V4 Flash 0731DeepSeek—$0.352$1.061M—100.0%2Open weights
18DeepSeek V4 Pro 0423DeepSeek—$1.42$2.831Mfp850.00%2Open weights
19DeepSeek V4.1 FlashDeepSeek—$0.18$0.721M—100.0%1Open weights
20GLM 5.1Z.ai—$1.33$4.18203Kfp8—1Open weights
21GLM 5.2Z.ai—$0.966$3.041Mfp883.34%3Open weights
22Qwen-PlusQwen—$0.26$0.781M—96.15%1
23Qwen3.5 Plus 2026-02-15Qwen—$0.26$1.561M—100.0%1
24Qwen3.5 Plus 2026-04-20Qwen—$0.30$1.801M—94.74%1
25Qwen3.5-27BQwen—$0.195$1.56262K—92.31%1Open weights
26Qwen3.5-35B-A3BQwen—$0.163$1.30262K—100.0%1Open weights
27Qwen3.5-FlashQwen—$0.065$0.261M—100.0%1
28Qwen3.6 27BQwen—$0.45$2.70262K—100.0%1Open weights
29Qwen3.6 FlashQwen—$0.188$1.131M—100.0%1
30Qwen3.6 PlusQwen—$0.325$1.951M—100.0%1
31Qwen3.7 FlashQwen—$0.03$0.131M—100.0%1
32Qwen3.7 MaxQwen—$1.48$4.421M—100.0%1
33Qwen3.8 Max (0803)Qwen—$2.00$6.001M—100.0%2
34Qwen3.8 Max (0902)Qwen—$2.00$6.001M—100.0%2

Alibaba on ModelCap: common questions

How many AI models does Alibaba serve?

34 tracked models as of 19 November 2026: 34 language models (13 with a public ModelCap Index position), across 44 live endpoints observed through OpenRouter.

What is the best model available on Alibaba?

Kimi K3.1 Pro from Moonshot AI is the highest-ranked language model Alibaba serves, at ModelCap Index position #11 and $10.00 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 K3.1 Pro, 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 96.34% 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 19 November 2026. Publication and page updates happen separately. Offers retained from a failed refresh are marked stale in the data and are not counted here.

Explore further