qwen3.6-plus
Creates a response from Qwen3.6-Plus. The model accepts text, image, and video content and supports function calling and structured output.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
AnyFast model ID.
qwen3.6-plus "qwen3.6-plus"
Conversation messages. Content may be text or an array of text, image, and video parts.
1Maximum number of generated tokens. Qwen3.6-Plus supports up to 64K output tokens.
1 <= x <= 65536Sampling temperature. Valid range is [0, 2). Set only one of temperature and top_p.
0 <= x < 21
Nucleus sampling probability. Valid range is (0, 1]. Set only one of temperature and top_p.
0 < x <= 1If true, stream partial message deltas using Server-Sent Events.
Options for streaming responses. Only relevant when stream is true.
An array of stop sequences. The string form is not supported by the current AnyFast endpoint.
Seed for more repeatable sampling.
0 <= x <= 2147483647Penalizes new tokens based on whether they appear in the text so far.
-2 <= x <= 2Penalizes repeated tokens based on their frequency in the text so far.
-2 <= x <= 2Controls reasoning mode. With the OpenAI SDK, pass this provider field through extra_body. Use non-thinking mode for workflows that require structured output or tool calling when required by the upstream model.
Application-defined functions or supported tools the model may call.
Controls whether the model calls tools or selects a function.
none, auto, required Structured output configuration. Use non-thinking mode when required by the upstream model.
Response
Completion generated successfully. The response is a complete completion when stream is false, or a completion chunk when stream is true.