# Alibaba Cloud

Alibaba Cloud serves 33 models on LLM API: 21 text models, 6 image models and 6 video models from Alibaba, DeepSeek, Moonshot AI and 1 other lab.

Model ID prefix: `alibaba/` (for text and image requests) · 33 models · 4 labs · [Alibaba Cloud privacy policy](https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy)
Updated: 2026-11-13
Canonical: https://llmapi.ai/providers/alibaba-cloud/

## Models and prices

Prices when Alibaba Cloud serves the request. A value in brackets is the price before the discount.

### Text (21)

Prices per 1M tokens.

| Model | Model ID | Input | Output | Cache read | Context |
| --- | --- | --- | --- | --- | --- |
| [DeepSeek V4.1 Flash 1017](https://llmapi.ai/models/deepseek-v4-1-flash-1017/) | `alibaba/deepseek-v4.1-flash-1017` | $0.15 | $0.6 | $0.015 | 1M |
| [Kimi K3](https://llmapi.ai/models/moonshotai-kimi-k3/) (−5%) | `alibaba/kimi-k3` | $2.85 (list $3) | $14.25 (list $15) | $0.285 (list $0.3) | 1.05M |
| [Qwen 3.8 Max](https://llmapi.ai/models/alibaba-qwen3-8-max/) (−15%) | `alibaba/qwen3.8-max` | $1.7 (list $2) | $5.1 (list $6) | $0.1445 (list $0.17) | 1M |
| [GLM-5.3](https://llmapi.ai/models/zhipu-glm-5-3/) (−30%) | `alibaba/glm-5.3` | $0.98 (list $1.4) | $3.08 (list $4.4) | $0.196 (list $0.28) | 1M |
| [DeepSeek V4.1 Flash](https://llmapi.ai/models/deepseek-deepseek-v4-1-flash/) | `alibaba/deepseek/deepseek-v4.1-flash` | $0.15 | $0.6 | $0.015 | 1M |
| [Qwen3.8 27B](https://llmapi.ai/models/qwen-qwen3-8-27b/) (−30%) | `alibaba/qwen/qwen3.8-27b` | $0.35 (list $0.5) | $2.1 (list $3) | $0.0139 (list $0.0199) | 262K |
| [DeepSeek V4 Flash 0731](https://llmapi.ai/models/deepseek-v4-flash-0731/) (−30%) | `alibaba/deepseek-v4-flash-0731` | $0.154 (list $0.22) | $0.462 (list $0.66) | $0.0154 (list $0.022) | 1M |
| [Kimi K2.7-Code](https://llmapi.ai/models/moonshotai-kimi-k2-7-code/) | `alibaba/kimi-k2.7-code` | $0.95 | $3.9995 | $0.1608 (list $0.1608) | 262K |
| [Qwen3.7 Max](https://llmapi.ai/models/qwen-qwen3-7-max/) (−40%) | `alibaba/qwen3.7-max` | $0.3 (list $0.5) | $1.8 (list $3) | — | 1M |
| [Qwen 3.7 Plus](https://llmapi.ai/models/alibaba-qwen3-7-plus/) (−40%) | `alibaba/qwen3.7-plus` | $0.3 (list $0.5) | $1.8 (list $3) | $0.03 (list $0.05) | 1M |
| [Qwen 3.6 Plus](https://llmapi.ai/models/qwen-qwen3-6-plus/) (−40%) | `alibaba/qwen3.6-plus` | $0.3 (list $0.5) | $1.8 (list $3) | $0.03 (list $0.05) | 1.05M |
| [Qwen3 Max](https://llmapi.ai/models/qwen-qwen3-max/) | `alibaba/qwen3-max` | $3 | $15 | $0.6 | 262K |
| [Qwen3 Coder Flash](https://llmapi.ai/models/alibaba-qwen3-coder-flash/) | `alibaba/qwen3-coder-flash` | $0.3 | $1.5 | $0.06 | 1M |
| [Qwen3 VL Plus](https://llmapi.ai/models/alibaba-qwen3-vl-plus/) | `alibaba/qwen3-vl-plus` | $0.2 | $1.6 | $0.04 | 262K |
| [Qwen Flash](https://llmapi.ai/models/alibaba-qwen-flash/) | `alibaba/qwen-flash` | $0.05 | $0.4 | $0.01 | 1M |
| [Qwen Plus](https://llmapi.ai/models/alibaba-qwen-plus/) | `alibaba/qwen-plus` | $0.4 | $1.2 | $0.08 | 131K |
| [Qwen Max](https://llmapi.ai/models/alibaba-qwen-max/) | `alibaba/qwen-max` | $1.6 | $6.4 | — | 131K |
| [Qwen Plus Latest](https://llmapi.ai/models/alibaba-qwen-plus-latest/) | `alibaba/qwen-plus-latest` | $0.4 | $1.2 | $0.08 | 1M |
| [Qwen 3.8 Flash](https://llmapi.ai/models/qwen-qwen3-8-flash/) (−15%) | `alibaba/qwen/qwen3.8-flash` | $0.0961 (list $0.113) | $0.3247 (list $0.382) | — | 1M |
| [Qwen 3.8 Max 0902](https://llmapi.ai/models/qwen-qwen3-8-max-0902/) (−15%) | `alibaba/qwen/qwen3.8-max-0902` | $1.4025 (list $1.65) | $4.2083 (list $4.951) | — | 1M |
| [Qwen 3.8 Omni Flash](https://llmapi.ai/models/qwen-qwen3-8-omni-flash/) (−15%) | `alibaba/qwen/qwen3.8-omni-flash` | $0.3655 (list $0.43) | $1.411 (list $1.66) | — | 1M |

### Image (6)

Price per image.

| Model | Model ID | Price | Modes |
| --- | --- | --- | --- |
| [Qwen Image Max 2025-12-30](https://llmapi.ai/models/alibaba-qwen-image-max-2025-12-30/) (−50%) | `alibaba/qwen-image-max-2025-12-30` | $0.0375 / image (list $0.075) | Generate |
| [Qwen Image](https://llmapi.ai/models/alibaba-qwen-image/) | `alibaba/qwen-image` | $0.035 / image | Generate |
| [Qwen Image Edit Max](https://llmapi.ai/models/alibaba-qwen-image-edit-max/) (−50%) | `alibaba/qwen-image-edit-max` | $0.04 / image (list $0.08) | Generate, Edit |
| [Qwen Image Edit Plus](https://llmapi.ai/models/alibaba-qwen-image-edit-plus/) (−50%) | `alibaba/qwen-image-edit-plus` | $0.02 / image (list $0.04) | Generate, Edit |
| [Qwen Image Max](https://llmapi.ai/models/alibaba-qwen-image-max/) (−50%) | `alibaba/qwen-image-max` | $0.0375 / image (list $0.075) | Generate |
| [Qwen Image Plus](https://llmapi.ai/models/alibaba-qwen-image-plus/) | `alibaba/qwen-image-plus` | $0.03 / image | Generate |

### Video (6)

Price per second of video; a range covers its resolutions.

| Model | Model ID | Per second | Generates from | Resolution |
| --- | --- | --- | --- | --- |
| [HappyHorse 1.1 Reference-to-Video](https://llmapi.ai/models/happyhorse-1-1-r2v/) (−60%) | `happyhorse-1.1-r2v` | $0.056–0.072 / second (list $0.14–0.18) | Reference | 720p–1080p |
| [HappyHorse 1.1 Text-to-Video](https://llmapi.ai/models/happyhorse-1-1-t2v/) (−60%) | `happyhorse-1.1-t2v` | $0.056–0.072 / second (list $0.14–0.18) | Text | 720p–1080p |
| [HappyHorse-1.0-Video-Edit](https://llmapi.ai/models/happyhorse-1-0-video-edit/) (−40%) | `happyhorse-1.0-video-edit` | $0.084–0.144 / second (list $0.14–0.24) | Video edit | 720p–1080p |
| [HappyHorse-1.1-I2V](https://llmapi.ai/models/happyhorse-1-1-i2v/) (−60%) | `happyhorse-1.1-i2v` | $0.056–0.072 / second (list $0.14–0.18) | Image | 720p–1080p |
| [wan3.0-video](https://llmapi.ai/models/wan3-0-video/) | `wan3.0-video` | $0.05–0.2 / second | Text, Image, Reference | 480p–1080p |
| [wan3.0-video-prime](https://llmapi.ai/models/wan3-0-video-prime/) | `wan3.0-video-prime` | $0.068–0.28 / second | Text, Image, Reference | 480p–1080p |

**Volume pricing.** At higher monthly volume, models on Alibaba Cloud may cost less. Book a call and sales will quote a price for your usage. [Book a call with sales](https://meetings.hubspot.com/julia-andriienko/llmapi) or [Create an account first](https://app.llmapi.ai/signup).

## Send requests to Alibaba Cloud

Put `alibaba/` before a model ID and the request goes to Alibaba Cloud. If Alibaba Cloud’s uptime over the last 5 minutes is below 90%, it goes to another provider of the model, unless it sends `X-No-Fallback: true`. [Routing docs](https://docs.llmapi.ai/features/routing)

Example: DeepSeek V4.1 Flash 1017, Chat Completions (`POST /v1/chat/completions`). Set LLMAPI_KEY to your LLM API key.

```python
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llmapi.ai/v1",
    api_key=os.environ["LLMAPI_KEY"],
)

response = client.chat.completions.create(
    model="alibaba/deepseek-v4.1-flash-1017",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)
```

Prices synced 2026-11-13.

Next step: [Get API key](https://app.llmapi.ai/signup)