Qwen3.8-Max VL
Qwen3.8-Max VL is Qwen’s multimodal reasoning model for working with text and images, with a one-million-token context window and support for tool calling and structured outputs.
Model
Qwen3.8-Max VL combines text and image understanding with reasoning and tool use. It can work with written prompts and visual inputs in the same conversation, making it useful for applications that need to interpret images alongside text.
The model supports a one-million-token context window, JSON mode, and structured outputs. Its reasoning controls let applications choose between direct responses and a higher-effort reasoning mode.
Shared Endpoint
On a Shared Endpoint, you pay per token. The endpoint is OpenAI-compatible and already live: point your existing SDK at it and start sending requests.