Alibaba CloudAIWS category: Reasoning & Multimodal
Qwen3.8-Max
Alibaba Cloud Qwen3.8-Max, a multimodal Model Studio API model with text, image, and video input.
Facts Verified
Sep 21, 2026
Verification
Verified
Profile
Source-backed
Context
1,000,000 tokens
Max output
131,072 tokens
API
Available
Specifications
Context
1,000,000 tokens
Max output
131,072 tokens
CompanyAlibaba Cloud
Release DateNot published
Provider statusNot published
LicenseNot published
API availabilityAvailable
Capability Map
Verified fieldsReasoning
Supported
Image input
Supported
Video input
Supported
API access
Available
Native input modalities
textimagevideo
Native output: text
Native output is what the model returns directly. Tool capabilities are separate.
Developer API Rates
Verified public rateInput / 1M
$1.65
Output / 1M
$4.95
Cached $0.2060 / 1MUS (Virginia) · Global scope
Cached input uses the documented implicit-cache rate for the US (Virginia), Global-scope deployment.
Verified Capabilities
- 1,000,000 tokens published context window
- 131,072 tokens published maximum output
- Reasoning support listed by the provider
- Multimodal input: text, image, video
Pricing & Availability Notes
- Stored pricing applies to US (Virginia) · Global scope
- Cached input uses the documented implicit-cache rate for the US (Virginia), Global-scope deployment.
Provider API model ID
Use this identifier in the provider API where supported.
qwen3.8-max