qwen-max
Last updated
Was this helpful?
Last updated
Was this helpful?
A large-scale Mixture-of-Experts (MoE) language model developed by Alibaba Cloud. It excels in language understanding, generation, and task performance across a variety of modalities. Mixture-of-Experts (MoE) Architecture: Uses 64 specialized "expert" networks, activating only relevant ones per task for efficient processing. Extensive Multilingual Support: Supports 29 languages, including Chinese, English, and Arabic. Long-Context Optimization: Supports 32K context windows with 8K generation. High Stability: Demonstrates high stability in maintaining prompt instructions, with no erroneous replies during extensive testing.
Only model
and messages
are required parameters for this model (and we’ve already filled them in for you in the example), but you can include optional parameters if needed to adjust the model’s behavior. Below, you can find the corresponding , which lists all available parameters along with notes on how to use them.
If you need a more detailed walkthrough for setting up your development environment and making a request step by step — feel free to use our .
Creates a chat completion using a language model, allowing interactive conversation by predicting the next response based on the given chat history. This is useful for AI-driven dialogue systems and virtual assistants.
512
false
JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so
Parameters for audio output. Required when audio output is requested with modalities: ["audio"]
Output types that you would like the model to generate
This tool searches the web for relevant results to use in a response
No content