curl --request POST \
--url https://api.powertokens.ai/v1/chat/completions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "qwen3.6-plus",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Hello, please introduce yourself."
}
],
"temperature": 0.7,
"max_tokens": 2000
}
'{
"id": "<string>",
"object": "chat.completion",
"created": 123,
"model": "<string>",
"choices": [
{
"index": 123,
"message": {
"role": "system",
"content": "<string>",
"tool_calls": [
{}
]
},
"finish_reason": "<string>"
}
],
"usage": {
"prompt_tokens": 123,
"completion_tokens": 123,
"total_tokens": 123
}
}Qwen chat completions
For the public chat models in the final Ali whitelist only: qwen3-max, qwen3.6-plus, qwen3.5-flash, qwen3-coder-plus, and deepseek-v3.2.
Public fields: model, messages, stream, temperature, top_p, max_tokens, stop, seed, tools, tool_choice, enable_search, and response_format.
curl --request POST \
--url https://api.powertokens.ai/v1/chat/completions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "qwen3.6-plus",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Hello, please introduce yourself."
}
],
"temperature": 0.7,
"max_tokens": 2000
}
'{
"id": "<string>",
"object": "chat.completion",
"created": 123,
"model": "<string>",
"choices": [
{
"index": 123,
"message": {
"role": "system",
"content": "<string>",
"tool_calls": [
{}
]
},
"finish_reason": "<string>"
}
],
"usage": {
"prompt_tokens": 123,
"completion_tokens": 123,
"total_tokens": 123
}
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
Model name. Only the public chat models in the final Ali whitelist are supported.
qwen3-max, qwen3.6-plus, qwen3.5-flash, qwen3-coder-plus, deepseek-v3.2 "qwen3.6-plus"
List of conversation messages. Supports text content and multimodal content (image+text).
Show child attributes
Show child attributes
Whether to use streaming output. Default is false.
Sampling temperature, controls output randomness. Range [0, 2].
0 <= x <= 2Nucleus sampling probability threshold.
0 <= x <= 1Maximum number of tokens to generate.
x >= 1List of stop sequences.
Random seed for reproducible generation.
List of tools for Function Calling.
Show child attributes
Show child attributes
Tool selection strategy. Options: auto, none, required.
Whether to enable search enhancement. Only some models support this.
Response format for forcing JSON output.
Show child attributes
Show child attributes
Response
Success, returns chat completion result. Streaming mode returns SSE stream.