{
"object": "list",
"data": [
{
"id": "qwen-turbo",
"object": "model",
"created": 1699999999,
"owned_by": "alibaba"
},
{
"id": "qwen-plus",
"object": "model",
"created": 1699999999,
"owned_by": "alibaba"
},
{
"id": "qwen-max",
"object": "model",
"created": 1699999999,
"owned_by": "alibaba"
}
]
}
curl --location --request GET 'https://zylalabs.com/api/13018/qwen+ai+api/26130/list+available+models' --header 'Authorization: Bearer YOUR_API_KEY'
{"choices":[{"finish_reason":"stop","index":0,"message":{"content":"Hello! How can I help you today?","reasoning_content":"Thinking Process:\n\n1. **Analyze the input:** The user said \"Hello\".\n2. **Determine the intent:** This is a standard greeting.\n3. **Formulate a response:**\n * Acknowledge the greeting.\n * Offer assistance.\n * Keep it polite, friendly, and open-ended.\n * *Examples:* \"Hello! How can I help you today?\", \"Hi there! What's on your mind?\", \"Greetings! How can I assist you?\"\n4. **Select the best response:** \"Hello! How can I help you today?\" is standard, polite, and effective.\n5. **Output the response.**","role":"assistant"}}],"created":1783012848,"id":"chatcmpl-ef622ad5-24a5-94ab-8696-828946aa1578","model":"qwen3.7-max","object":"chat.completion","usage":{"completion_tokens":162,"completion_tokens_details":{"reasoning_tokens":148},"prompt_tokens":11,"prompt_tokens_details":{"cached_tokens":0},"total_tokens":173}}
curl --location --request POST 'https://zylalabs.com/api/13018/qwen+ai+api/26341/chat' --header 'Authorization: Bearer YOUR_API_KEY'
--data-raw '{
"model": "qwen3.7-max",
"messages": [
{
"role": "user",
"content": "Hello"
}
]
}'
注册后,每个开发者都会被分配一个个人 API 访问密钥,这是一个唯一的字母和数字组合,用于访问我们的 API 端点。要使用 Qwen AI API 进行身份验证,只需在 Authorization 标头中包含您的 bearer token。
| 标头 | 描述 |
|---|---|
授权
|
必需
应为 Bearer access_key. 订阅后,请查看上方的"您的 API 访问密钥"。
|
无长期承诺。随时升级、降级或取消。 免费试用包括最多 50 个请求。
(年度计费可节省 2 个月 🎉)
API for Alibaba Qwen large language models supporting text generation, reasoning, and vision. OpenAI-compatible endpoints with context up to 1M tokens.
Models: qwen-max, qwen-plus, qwen-turbo, qwen-vl-max, qwen-vl-plus.
Features: chat completions, system prompts, function calling, streaming, image input. Authentication via Bearer token.
The List Available Models endpoint returns a list of model specifications, including model IDs, names, and context window sizes. The Vision Chat Image Analysis endpoint returns image analysis results, including descriptions, visual question answers, and usage statistics like token counts.
For the List Available Models, key fields include "id," "object," "created," and "owned_by." In the Vision Chat Image Analysis response, important fields are "id," "model," "choices," and "usage," which details token counts for prompts and completions.
The List Available Models response is structured as an object containing a "data" array of model objects. The Vision Chat Image Analysis response includes an "id," "model," and a "choices" array, where each choice contains a "message" with the analysis content and a "usage" object detailing token usage.
The Vision Chat Image Analysis endpoint accepts parameters such as the image file (in supported formats) and any specific questions related to the image. Users can customize requests by specifying the type of analysis or questions they want answered.
Typical use cases include generating text based on prompts, analyzing images for descriptions or answering questions about visual content, and extracting text from images using OCR capabilities. These functionalities can be applied in various fields like education, content creation, and accessibility.
Data accuracy is maintained through rigorous training of the Qwen models on diverse datasets and continuous updates to improve performance. The models are designed to provide reliable outputs based on extensive testing and validation processes.
用户可以通过解析响应结构来提取相关信息,例如模型能力或图像分析结果,从而利用返回的数据。例如,他们可以在视觉聊天响应中使用“内容”字段来在应用程序中显示图像描述或答案
Users can expect structured responses with consistent fields across requests. For example, the Vision Chat responses will typically include a detailed analysis in the "content" field and token usage metrics, allowing users to gauge the complexity of their queries and the model's performance.