> ## Documentation Index > Fetch the complete documentation index at: https://powower.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # qwen3.7-plus Chat Completions > Applicable to the qwen3.7-plus model in the Ali channel. Supported fields: `model`, `messages`, `stream`, `temperature`, `top_p`, `top_k`, `repetition_penalty`, `presence_penalty`, `max_completion_tokens`, `max_tokens`, `stop`, `seed`, `tools`, `tool_choice`, `parallel_tool_calls`, `enable_search`, `search_options`, `response_format`, `enable_thinking`, `thinking_budget`, `reasoning_effort`, `tool_stream`, `enable_code_interpreter`, `vl_high_resolution_images`, `n`, `logprobs`, `top_logprobs`, `preserve_thinking`, `skill`, `clear_thinking`. ## OpenAPI ````yaml api-reference/en/zmodelChat/ali/qwen3.7-plus.json POST /v1/chat/completions openapi: 3.0.1 info: title: qwen3.7-plus Chat Completions version: 1.0.0 description: >- Ali chat capability documentation. The unified API endpoint is /v1/chat/completions. license: name: Project License url: https://github.com/QuantumNous/new-api/blob/main/LICENSE servers: - url: https://baze-api.powerbuyin.top description: Baze API endpoint security: [] tags: - name: Qwen Chat description: Qwen series chat and multimodal capabilities paths: /v1/chat/completions: post: tags: - Qwen Chat summary: qwen3.7-plus Chat Completions description: >- Applicable to the qwen3.7-plus model in the Ali channel. Supported fields: `model`, `messages`, `stream`, `temperature`, `top_p`, `top_k`, `repetition_penalty`, `presence_penalty`, `max_completion_tokens`, `max_tokens`, `stop`, `seed`, `tools`, `tool_choice`, `parallel_tool_calls`, `enable_search`, `search_options`, `response_format`, `enable_thinking`, `thinking_budget`, `reasoning_effort`, `tool_stream`, `enable_code_interpreter`, `vl_high_resolution_images`, `n`, `logprobs`, `top_logprobs`, `preserve_thinking`, `skill`, `clear_thinking`. operationId: aliChatCompletions requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ChatCompletionRequest' examples: Text input: summary: Text input value: model: qwen3.7-plus messages: - role: system content: You are a helpful assistant. - role: user content: Who are you? Streaming output: summary: Streaming output value: model: qwen3.7-plus messages: - role: system content: You are a helpful assistant. - role: user content: Who are you? stream: true stream_options: include_usage: true Image input: summary: Image input value: model: qwen-vl-plus messages: - role: user content: - type: image_url image_url: url: >- https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg - type: text text: What is this? Video input: summary: Video input value: model: qwen-vl-max messages: - role: user content: - type: video video: - >- https://img.alicdn.com/imgextra/i3/O1CN01K3SgGo1eqmlUgeE9b_!!6000000003923-0-tps-3840-2160.jpg - >- https://img.alicdn.com/imgextra/i4/O1CN01BjZvwg1Y23CF5qIRB_!!6000000003000-0-tps-3840-2160.jpg - >- https://img.alicdn.com/imgextra/i4/O1CN01Ib0clU27vTgBdbVLQ_!!6000000007859-0-tps-3840-2160.jpg - >- https://img.alicdn.com/imgextra/i1/O1CN01aygPLW1s3EXCdSN4X_!!6000000005710-0-tps-3840-2160.jpg - type: text text: Describe this video in detail. Tool calling: summary: Tool calling value: model: qwen-plus messages: - role: system content: You are a helpful assistant. - role: user content: How is the weather in Hangzhou? tools: - type: function function: name: get_current_time description: Useful when you want to know the current time. parameters: {} - type: function function: name: get_current_weather description: >- Useful when you want to query the weather for a specific city. parameters: type: object properties: location: type: string description: >- City or district, e.g., Beijing, Hangzhou, Yuhang District. required: - location Web search: summary: Web search value: model: qwen-plus messages: - role: system content: You are a helpful assistant. - role: user content: >- How many gold medals did China win at the Paris Olympics? enable_search: true Document understanding: summary: Document understanding value: model: qwen-long messages: - role: system content: You are a helpful assistant. - role: system content: fileid://file-fe-xxx - role: user content: What is this article about? stream: true stream_options: include_usage: true PPT generation: summary: PPT generation value: model: qwen-doc-turbo messages: - role: system content: you are a helpful assistant. - role: system content: Your document content - role: user content: Generate a 10-20 page PPT skill: - type: ppt mode: general template_id: news_01 stream: true stream_options: include_usage: true responses: '200': description: Success. Returns chat completions. Streaming returns SSE. content: application/json: schema: oneOf: - $ref: '#/components/schemas/ChatCompletionResponse' title: Chat response object (non-streaming) - $ref: '#/components/schemas/ChatCompletionChunkResponse' title: Chat response chunk object (streaming) examples: Non-streaming response example: summary: Non-streaming response example value: choices: - message: role: assistant content: >- I am a large-scale language model developed by Alibaba Cloud. My name is Qianwen. finish_reason: stop index: 0 logprobs: null object: chat.completion usage: prompt_tokens: 3019 completion_tokens: 104 total_tokens: 3123 prompt_tokens_details: cached_tokens: 2048 created: 1735120033 system_fingerprint: null model: qwen-plus id: chatcmpl-6ada9ed2-7f33-9de2-8bb0-78bd4035025a Streaming response example (multi-chunk, SSE): summary: Streaming response example (multi-chunk, SSE) value: - id: chatcmpl-e30f5ae7-3063-93c4-90fe-beb5f900bd57 choices: - delta: content: '' function_call: null refusal: null role: assistant tool_calls: null finish_reason: null index: 0 logprobs: null created: 1735113344 model: qwen-plus object: chat.completion.chunk service_tier: null system_fingerprint: null usage: null - id: chatcmpl-e30f5ae7-3063-93c4-90fe-beb5f900bd57 choices: - delta: content: 我是 function_call: null refusal: null role: null tool_calls: null finish_reason: null index: 0 logprobs: null created: 1735113344 model: qwen-plus object: chat.completion.chunk service_tier: null system_fingerprint: null usage: null - id: chatcmpl-e30f5ae7-3063-93c4-90fe-beb5f900bd57 choices: - delta: content: 来自 function_call: null refusal: null role: null tool_calls: null finish_reason: null index: 0 logprobs: null created: 1735113344 model: qwen-plus object: chat.completion.chunk service_tier: null system_fingerprint: null usage: null - id: chatcmpl-e30f5ae7-3063-93c4-90fe-beb5f900bd57 choices: - delta: content: 阿里 function_call: null refusal: null role: null tool_calls: null finish_reason: null index: 0 logprobs: null created: 1735113344 model: qwen-plus object: chat.completion.chunk service_tier: null system_fingerprint: null usage: null - id: chatcmpl-e30f5ae7-3063-93c4-90fe-beb5f900bd57 choices: - delta: content: 云的超大规模 function_call: null refusal: null role: null tool_calls: null finish_reason: null index: 0 logprobs: null created: 1735113344 model: qwen-plus object: chat.completion.chunk service_tier: null system_fingerprint: null usage: null - id: chatcmpl-e30f5ae7-3063-93c4-90fe-beb5f900bd57 choices: - delta: content: 语言模型，我 function_call: null refusal: null role: null tool_calls: null finish_reason: null index: 0 logprobs: null created: 1735113344 model: qwen-plus object: chat.completion.chunk service_tier: null system_fingerprint: null usage: null - id: chatcmpl-e30f5ae7-3063-93c4-90fe-beb5f900bd57 choices: - delta: content: 叫千问千 function_call: null refusal: null role: null tool_calls: null finish_reason: null index: 0 logprobs: null created: 1735113344 model: qwen-plus object: chat.completion.chunk service_tier: null system_fingerprint: null usage: null - id: chatcmpl-e30f5ae7-3063-93c4-90fe-beb5f900bd57 choices: - delta: content: 问。 function_call: null refusal: null role: null tool_calls: null finish_reason: null index: 0 logprobs: null created: 1735113344 model: qwen-plus object: chat.completion.chunk service_tier: null system_fingerprint: null usage: null - id: chatcmpl-e30f5ae7-3063-93c4-90fe-beb5f900bd57 choices: - delta: content: '' function_call: null refusal: null role: null tool_calls: null finish_reason: stop index: 0 logprobs: null created: 1735113344 model: qwen-plus object: chat.completion.chunk service_tier: null system_fingerprint: null usage: null - id: chatcmpl-e30f5ae7-3063-93c4-90fe-beb5f900bd57 choices: [] created: 1735113344 model: qwen-plus object: chat.completion.chunk service_tier: null system_fingerprint: null usage: completion_tokens: 17 prompt_tokens: 22 total_tokens: 39 completion_tokens_details: null prompt_tokens_details: audio_tokens: null cached_tokens: 0 '400': description: Invalid request parameters. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: invalid_request: summary: 参数错误 value: error: message: messages is required type: invalid_request_error code: bad_request_body param: messages '401': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: unauthorized: summary: 未授权 value: error: message: Invalid token type: api_error code: access_denied param: '' description: Authentication failed. '429': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: quota_exceeded: summary: 额度不足或速率受限 value: error: message: Rate limit exceeded type: api_error code: insufficient_user_quota param: '' description: Rate limit exceeded or quota exhausted. '500': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: internal_error: summary: 内部处理失败 value: error: message: Internal server error type: api_error code: gen_relay_info_failed param: '' description: Internal server error. '502': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: bad_gateway: summary: 上游响应异常 value: error: message: Invalid upstream response type: api_error code: bad_response_status_code param: '' description: Upstream response error. '503': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: service_unavailable: summary: 服务暂不可用 value: error: message: Service temporarily unavailable type: api_error code: get_channel_failed param: '' description: Upstream service unavailable. security: - BearerAuth: [] components: schemas: ChatCompletionRequest: type: object required: - model - messages properties: model: type: string enum: - qwen3.7-plus description: >- Model name. Only publicly available chat models in the current Ali channel's final whitelist are supported. example: qwen3.7-plus messages: type: array description: >- Context passed to the model, arranged in conversation order. Supports four message types: System Message, User Message, Assistant Message, and Tool Message. Supports plain text, multimodal (image/video/audio) content, and explicit caching. items: oneOf: - $ref: '#/components/schemas/SystemMessage' title: System Message object (optional) - $ref: '#/components/schemas/UserMessage' title: User Message object (required) - $ref: '#/components/schemas/AssistantMessage' title: Assistant Message object (optional) - $ref: '#/components/schemas/ToolMessage' title: Tool Message object (optional) stream: type: boolean description: >- Whether to stream the response. Values: - false: Returns the entire content at once after generation completes; - true: Streams output as it is generated, returning each chunk as it becomes available. Chunks must be read in real time and concatenated to assemble the full response. Recommended to set to true for better reading experience and lower timeout risk. Note: Non-streaming calls that do not complete within 300 seconds will be interrupted and return the already generated content (not an error). Streaming is strongly recommended for longer outputs. default: false stream_options: type: object description: Stream output configuration. Only effective when stream is true. properties: include_usage: type: boolean description: >- Whether to include token usage information in the last chunk of the response. Values: true (include), false (do not include). When streaming, token usage information only appears in the last chunk of the response. default: false temperature: type: number description: >- Sampling temperature, controlling the diversity of generated text. Higher temperature produces more diverse output; lower temperature produces more deterministic output. Range: [0, 2). temperature and top_p both control text diversity; it is recommended to set only one of them. minimum: 0 maximum: 2 default: 0.7 top_p: type: number description: >- Nucleus sampling probability threshold, controlling text diversity. Higher top_p produces more diverse output; lower top_p produces more deterministic output. Range: (0, 1.0]. temperature and top_p both control text diversity; it is recommended to set only one of them. minimum: 0 maximum: 1 default: 0.95 stop: oneOf: - type: string description: Stop sequence string. - type: array items: type: string description: List of stop sequences. description: >- Used to specify stop sequences. When the text generated by the model contains a string specified by stop, generation will terminate immediately. Sensitive words can be passed to control model output. When stop is an array, token_id and strings cannot be mixed as elements. For example, specifying ["hello", 104307] is not allowed. seed: type: integer description: >- Random seed. Used to ensure reproducible results with the same input and parameters. If called with the same seed and other parameters unchanged, the model will return the same results as much as possible. Range: [0, 2^31−1]. Seed defaults: - qwen-vl-max, qvq-max series: 3407; - qwen-vl-max-2024-02-01, qwen-vl-plus: no default; - All other models: 1234. minimum: 0 maximum: 2147483647 tools: type: array description: >- An array of one or more tool objects for the model to call in Function Calling. When tools is set and the model determines a tool call is needed, the response returns tool information through tool_calls. Properties: - type (required): Tool type, currently only supports function. - function (required): Tool and parameter information. - name (required): Tool name. Only allows letters, numbers, underscores (_) and dashes (-), up to 64 tokens. - description (required): Tool description to help the model determine when and how to call the tool. - parameters (optional, default {}): Tool parameter description, must be a valid JSON Schema. If parameters is empty, the tool has no input parameters (e.g., time query tool). It is recommended to pass parameters to improve tool call accuracy. items: $ref: '#/components/schemas/Tool' tool_choice: oneOf: - type: string enum: - auto - none - required description: >- Tool choice strategy: auto (model decides), none (disable tools), required (must call at least one tool). - type: object properties: type: type: string function: type: object properties: name: type: string description: >- Force specific tool: {"type":"function","function":{"name":"the_function_to_call"}}. Thinking models do not support forcing a specific tool. description: >- Tool selection strategy. Default: auto. To force a specific tool call method for a type of question (e.g., always use a tool or disable all tools), set this parameter. Values: - auto: The model autonomously selects the tool strategy; - none: If you do not want tool calls, set tool_choice to none; - {"type": "function", "function": {"name": "the_function_to_call"}}: If you want to force a specific tool call, set this parameter where the_function_to_call is the specified tool function name. Thinking models do not support forcing a specific tool call. default: auto enable_search: type: boolean description: >- Whether to enable web search. Default: false. Values: - true: Enabled. If web search is not triggered after enabling, optimize the prompt or set forced_search in search_options to force search; - false: Disabled. Enabling web search may increase token consumption. This parameter is not an OpenAI standard parameter. When calling through the Python SDK, place it in the extra_body object: extra_body={"enable_search": True}. default: false response_format: type: object description: >- Format of the response. Values: - {"type": "text"}: Returns text response; - {"type": "json_object"}: Returns a standard JSON string. Related doc: Structured Output. If set to {"type": "json_object"}, you must explicitly instruct the model to output JSON in the prompt, e.g., "Please output in JSON format", otherwise an error will occur. properties: type: type: string enum: - text - json_object description: 'Response format type. Values: text, json_object.' top_k: type: integer description: >- Specifies the number of candidate tokens for sampling during generation. Higher values produce more random output; lower values produce more deterministic output. If set to null or greater than 100, the top_k strategy is disabled and only the top_p strategy takes effect. The value must be an integer greater than or equal to 0. Default: 20. This parameter is not an OpenAI standard parameter. When calling through the Python SDK, place it in the extra_body object: extra_body={"top_k":xxx}. minimum: 0 default: 20 repetition_penalty: type: number description: >- Controls the repetition degree in continuous sequences during model generation. Increasing repetition_penalty reduces repetition; 1.0 means no penalty. No strict value range, as long as it is greater than 0. repetition_penalty defaults: - qwen-max, qwen-math, qwen-vl-max, qwen-audio-turbo, QVQ, QwQ, Qwen3-VL: 1.0; - qwen-coder, qwen2-1.5b-instruct, qwen2-0.5b-instruct, qwen2.5-omni-7b: 1.1; - qwen-vl-plus: 1.2; - All other models: 1.05. This parameter is not an OpenAI standard parameter. When calling through the Python SDK, place it in the extra_body object: extra_body={"repetition_penalty":xxx}. minimum: 0 default: 1.05 presence_penalty: type: number description: >- Controls content repetition during model generation. Range: [-2.0, 2.0]. Positive values reduce repetition; negative values increase repetition. For creative writing or brainstorming scenarios requiring diversity, fun, or creativity, it is recommended to increase this value; for technical documentation or formal text requiring consistency and terminology accuracy, it is recommended to decrease this value. presence_penalty defaults: - Qwen3.7 (non-thinking), Qwen3.6 (non-thinking), Qwen3.5-Omni, Qwen3.5 (non-thinking), qwen3-max-preview (thinking), Qwen3 (non-thinking), Qwen3-Instruct 1.7b/4b (thinking), QVQ, qwen-max, qwen2.5-vl, qwen-vl-max, qwen-vl-plus, Qwen3-VL (non-thinking): 1.5; - qwen3-8b/14b/32b/30b-a3b/235b-a22b (thinking), qwen-plus/qwen-plus-latest/2025-04-28 (thinking), qwen-turbo/qwen-turbo/2025-04-28 (thinking): 0.5; - All others: 0.0. Principle: When the parameter is positive, the model imposes a penalty on tokens already present in the current text (independent of frequency), reducing the probability of repeated occurrences, thereby reducing content repetition and increasing vocabulary diversity. minimum: -2 maximum: 2 default: 1.5 max_completion_tokens: type: integer description: >- Maximum length of model output, including thinking content and model response. Generation stops early when this value is exceeded, with finish_reason set to length. Default and maximum values are the model's maximum output length. Difference from max_tokens: max_completion_tokens limits the full model output (thinking + response), while max_tokens limits only the response portion. Thinking models recommend using max_completion_tokens. Supported models: - Qianwen Max: Qwen3.7-Max and later models - Qianwen Plus: Qwen3.5-Plus and later models The actual output token count may have an error of up to 10 tokens from the set max_completion_tokens value. minimum: 1 parallel_tool_calls: type: boolean description: |- Whether to enable parallel tool calls. Default: false. Values: - true: Enabled; - false: Disabled. default: false search_options: type: object description: >- Strategy for web search. This parameter is not an OpenAI standard parameter. When calling through the Python SDK, place it in the extra_body object: extra_body={"search_options": xxx}. enable_thinking: type: boolean description: >- When using mixed-thinking models (which can think or not think before responding), controls whether to enable thinking mode. Applies to Qwen3.7, Qwen3.6, Qwen3.5, Qwen3, Qwen3-Omni-Flash, Qwen3-VL models, and DeepSeek-V4-Pro/V4-Flash series (Aliyun direct supply), DeepSeek-V3.2/V3.2-exp/V3.1 series (Aliyun direct supply, SiliconFlow direct supply, Kuaishou Wanqing direct supply), Kimi-K2.7-code (thinking-only model), Kimi-K2.6/K2.5 series (Aliyun direct supply, Moonshot direct supply), GLM series. DeepSeek-V4 series enables thinking by default, adjustable via reasoning_effort. Values: - true: Enabled. When enabled, thinking content is returned via the reasoning_content field. - false: Disabled. Default values vary by supported model. This parameter is not an OpenAI standard parameter. When calling through the Python SDK, place it in the extra_body object: extra_body={"enable_thinking": xxx}. If not using the OpenAI SDK but calling directly via HTTP (such as curl), no extra_body is needed. Instead, place enable_thinking at the top level of the request body alongside model, messages, and other parameters, e.g., "enable_thinking": true. thinking_budget: type: integer description: >- Maximum number of tokens in the thinking process. Applies to Qwen3.7, Qwen3.6, Qwen3.5, Qwen3-VL, Qwen3, GLM (Aliyun direct supply), Kimi (Aliyun direct supply) series models. Related doc: Limiting Thinking Length. Default value is the model's maximum thinking chain length. Refer to: Model List. This parameter is not an OpenAI standard parameter. When calling through the Python SDK, place it in the extra_body object: extra_body={"thinking_budget": xxx}. minimum: 1 reasoning_effort: type: string description: >- Controls the model's reasoning effort. Different models support different values and defaults. DeepSeek-V4, GLM series and kimi/kimi-k3 (default: high): - Values: high (high reasoning effort), max (maximum reasoning effort). low and medium map to high, xhigh maps to max. - Applies to glm-5.2, glm-5.1, glm-5, deepseek-v4-pro, deepseek-v4-flash (Aliyun direct supply), kimi/kimi-k3 (Moonshot direct supply, max only). qwen3.8-max-preview model (default: xhigh): - Values: xhigh (high reasoning effort), medium (medium reasoning effort), low (low reasoning effort). max maps to xhigh, high maps to xhigh, minimal maps to low, none maps to enable_thinking=False. Setting values other than these options and mappings will cause an error. Important: qwen3.8-max-preview does not support setting reasoning_effort and thinking_budget simultaneously; setting both will cause an error. However, they support mutual conversion: - When thinking_budget is not set, reasoning_effort levels automatically map to thinking_budget: low corresponds to 4096, medium to 16384, xhigh to 262144. - When reasoning_effort is not set, thinking_budget automatically maps back to reasoning_effort: 0~4096 corresponds to low, 4097~16384 to medium, 16385~262144 to xhigh. - When neither is set, the default thinking_budget (131072) and default reasoning_effort (xhigh) are used. This parameter is not an OpenAI standard parameter. When calling through the Python SDK, place it in the extra_body object: extra_body={"reasoning_effort": "high"}. enum: - low - medium - high - max - xhigh tool_stream: type: boolean description: >- Only takes effect when stream=true. Currently only Qwen and GLM series support this. Default: false. Qwen series support list: - qwen-max series: text modality of qwen3.7-max series; - qwen-plus series: text modality of qwen3.7-plus and qwen3.6-plus series, and full modality of qwen3.5-plus series; - qwen-flash series: full modality of qwen3.7-flash, qwen3.6-flash, and qwen3.5-flash series. Qwen series usage reference: tool_stream only affects complex tool parameters. Simple tool parameters will stream output as long as stream=true is enabled. Complex tools are tools where some parameter types are array or object. - tool_stream=false: Complex tool parameters are output at once, default behavior, complex format is more accurate; - tool_stream=true: Complex tool parameters are streamed output, no timeout risk for complex format. This parameter is not an OpenAI standard parameter. When calling through the Python SDK, place it in the extra_body object: extra_body={"tool_stream": true}. default: false enable_code_interpreter: type: boolean description: >- Whether to enable the code interpreter feature. Default: false. Values: - true: Enabled; - false: Disabled. This parameter is not an OpenAI standard parameter. When calling through the Python SDK, place it in the extra_body object: extra_body={"enable_code_interpreter": xxx}. default: false vl_high_resolution_images: type: boolean description: >- Whether to increase the input image pixel limit to the pixel value corresponding to 16384 tokens. Related doc: Processing High-Resolution Images. Default: false. When vl_high_resolution_images is true: Uses a fixed resolution strategy, ignoring the max_pixels setting. When the resolution is exceeded, the total image pixels are scaled down to this limit. When vl_high_resolution_images is true, different models have different pixel limits: - Qwen3.7, Qwen3.6, Qwen3.5, Qwen3-VL series, qwen-vl-max, qwen-vl-max-0813, qwen-vl-plus, qwen-vl-plus-0815, qwen-vl-plus-0710: 16777216 (each token corresponds to 32×32 pixels, i.e., 16384×32×32); - QVQ series and other Qwen2.5-VL models: 12845056 (each token corresponds to 28×28 pixels, i.e., 16384×28×28). When vl_high_resolution_images is false: The pixel limit is determined by max_pixels. When input image pixels exceed max_pixels, the image is scaled down to within max_pixels. The default pixel limit for each model is the default value of max_pixels. This parameter is not an OpenAI standard parameter. When calling through the Python SDK, place it in the extra_body object: extra_body={"vl_high_resolution_images":xxx}. default: false 'n': type: integer description: >- Number of responses, range 1-4. Only supported by certain models. Default: 1. minimum: 1 maximum: 4 default: 1 logprobs: type: boolean description: >- Whether to return log probabilities of output tokens. Default: false. Values: - true: Return; - false: Do not return. Content generated during the thinking phase (reasoning_content) does not return log probabilities. Supported models: - Snapshot models of qwen-plus series (excluding stable models); - Snapshot models of qwen-turbo series (excluding stable models); - qwen3-vl-plus series models (including stable models); - qwen3-vl-flash series models (including stable models); - Qwen3 open-source models. default: false top_logprobs: type: integer description: >- Specifies the number of candidate tokens with the highest probability for the model to return at each generation step. Default: 0. Range: [0, 5]. Only takes effect when logprobs is true. minimum: 0 maximum: 5 default: 0 preserve_thinking: type: boolean description: >- Whether to concatenate historical assistant reasoning_content into model input. Suitable for scenarios requiring the model to reference historical thinking processes. Default: false. Currently supported: qwen3.8-max-preview (enabled by default), qwen3.7-max, qwen3.7-max-2026-05-20 and later snapshots, qwen3.6-max-preview, qwen3.7-plus, qwen3.7-plus-2026-05-26, qwen3.6-plus, qwen3.6-plus-2026-04-02, qwen3.7-flash, qwen3.7-flash-2026-07-15, qwen3.6-flash, qwen3.6-flash-2026-04-16, kimi-k2.6 (Aliyun Bailian deployment), kimi-k2.7-code (Aliyun Bailian deployment, enabled by default), kimi/kimi-k2.7-code-highspeed (Moonshot direct supply, enabled by default), kimi/kimi-k2.7-code (Moonshot direct supply, enabled by default). Important: When using qwen3.8-max-preview, preserve_thinking defaults to true and all historical reasoning_content must be passed back completely. Concatenating reasoning_content into the content field for playback is not supported. If historical messages do not contain reasoning_content, enabling this parameter will not cause errors and is compatible. When enabled, historical reasoning_content counts toward input tokens and is billed accordingly. This parameter is not an OpenAI standard parameter. When calling through the Python SDK, place it in the extra_body object: extra_body={"preserve_thinking": True}. default: false thinking: type: object description: >- Controls thinking mode for MiniMax/MiniMax-M3 (supplied by 稀宇科技). Default: {"type":"adaptive"}. Non-standard parameter, use extra_body. properties: type: type: string enum: - adaptive - disabled description: >- Thinking type. Values: adaptive (model decides), disabled (direct answer). skill: type: array description: >- Skill parameter for enabling specific generation skills (e.g., PPT generation). Only supported by qwen-doc-turbo model. Default: []. This parameter is not an OpenAI standard parameter. When calling through the Python SDK, place it in the extra_body object: extra_body={"skill": [...]}. When using skill, stream must be set to true. Properties: - type (required): Skill type. Currently supports: ppt (PPT generation). - mode (optional): PPT generation mode. Values: general (default, template mode, requires template_id, generates HTML format PPT), creative (creative mode, no template needed, generates image-based PPT with each page as an image). - template_id (optional): PPT template ID. Used with mode=general or when mode is not set. Values: news_01 (news template), summary_01 (summary template), internet_01 (internet template), thesis_01 (thesis template). items: type: object properties: type: type: string description: 技能类型。当前支持：ppt（PPT 生成）。 mode: type: string enum: - general - creative description: >- PPT 生成模式。可选值：general（默认，模板模式，需配合 template_id 使用，生成 HTML 格式的 PPT）、creative（创意模式，无需模板，生成图版 PPT）。 template_id: type: string description: >- PPT 模板 ID。可选值：news_01（新闻模板）、summary_01（总结模板）、internet_01（互联网模板）、thesis_01（论文模板）。 clear_thinking: type: boolean description: >- Controls whether historical reasoning_content (thinking process) is used as context input to the model in multi-turn conversations. Only supported by GLM series glm-5.2, glm-5.1, glm-5, glm-4.7 models. Default: false. This parameter is not an OpenAI standard parameter. When calling through the Python SDK, place it in the extra_body object: extra_body={"enable_thinking": True,"clear_thinking": True}. - true: Ignores historical reasoning_content and uses only non-reasoning content such as visible text, tool calls and results as context input, which can reduce context length and cost; - false (default): Preserves historical reasoning_content and provides it to the model along with context. If Preserved Thinking is to be enabled, historical reasoning_content must be passed through completely, unmodified, and in original order in messages. Missing, truncation, rewriting, or reordering will cause degraded or ineffective results. default: false X-DashScope-DataInspection: type: string description: >- Based on the content security capability of the Qianwen API, whether to further identify violations in input and output content. Values: - {"input":"cip","output":"cip"}: Further identification; - Not set: No further identification. When calling via HTTP, place in the request header: -H "X-DashScope-DataInspection: {\"input\": \"cip\", \"output\": \"cip\"}"; When calling through the Python SDK, configure via extra_headers: extra_headers={'X-DashScope-DataInspection': '{"input":"cip","output":"cip"}'}. Not supported via Node.js SDK. ChatCompletionResponse: type: object properties: id: type: string description: Unique identifier for this call. object: type: string example: chat.completion description: Always chat.completion. created: type: integer format: int64 description: Unix timestamp (seconds). model: type: string description: Model used for this request. choices: type: array items: $ref: '#/components/schemas/Choice' description: Array of generated responses. usage: $ref: '#/components/schemas/Usage' description: Token usage information. service_tier: type: string nullable: true description: Currently fixed to null. system_fingerprint: type: string nullable: true description: Currently fixed to null. ChatCompletionChunkResponse: type: object description: Chunk object structure for streaming responses. properties: id: type: string description: Unique identifier for this call. Each chunk object has the same id. choices: type: array description: >- Array of generated content. If include_usage is true, choices is an empty array in the last chunk. items: $ref: '#/components/schemas/ChunkChoice' created: type: integer format: int64 description: Timestamp when this request was created. model: type: string description: Model used for this request. object: type: string example: chat.completion.chunk description: Always chat.completion.chunk. service_tier: type: string nullable: true description: Currently fixed to null. system_fingerprint: type: string nullable: true description: Currently fixed to null. usage: $ref: '#/components/schemas/Usage' description: Token usage. Only shown in last chunk when include_usage is true. ErrorResponse: type: object properties: error: type: object properties: message: type: string type: type: string description: 错误类型，例如 `invalid_request_error`、`api_error` 或上游兼容错误类型。 code: type: string SystemMessage: type: object required: - role - content description: >- System message. Used to set the model's role, tone, task goals, or constraints. Typically placed first in the messages array. properties: role: type: string enum: - system description: 'System message role. Fixed value: system.' content: type: string description: >- System instruction. Used to define the model's role, behavior, response style, and task constraints. title: System Message object (optional) UserMessage: type: object required: - role - content description: >- User message. Used to pass questions, instructions, or context to the model. properties: role: type: string enum: - user description: 'User message role. Fixed value: user.' content: anyOf: - type: string description: Plain text content. - type: array description: Multimodal content list (image/video/audio). items: $ref: '#/components/schemas/ContentItem' description: >- Message content. string for plain text; array for multimodal content or explicit caching. title: User Message object (required) AssistantMessage: type: object required: - role description: Model response. Typically used as context for multi-turn conversations. properties: role: type: string enum: - assistant description: 'Assistant message role. Fixed value: assistant.' content: type: string description: >- Model's text response. Can be empty when tool_calls is present; otherwise required. tool_calls: type: array description: Tool call information returned by the model after Function Calling. items: $ref: '#/components/schemas/ToolCall' partial: type: boolean description: 'Whether to enable prefix continuation. Default: false.' default: false reasoning_content: type: string description: Model thinking content. title: Assistant Message object (optional) ToolMessage: type: object required: - role - content - tool_call_id description: Tool output message. properties: role: type: string enum: - tool description: 'Fixed value: tool.' content: type: string description: Tool function output. Must be a string. tool_call_id: type: string description: >- ID returned after Function Calling, used to associate the Tool Message with the corresponding tool. title: Tool Message object (optional) Tool: type: object required: - type properties: type: type: string enum: - function description: Tool type. Currently only function. function: type: object required: - name - description description: Tool information. properties: name: type: string description: >- Tool name. Allows letters, numbers, underscores, hyphens. Max 64 tokens. description: type: string description: >- Tool description to help the model determine when and how to call. parameters: type: object description: >- Tool parameter definition. Must be a valid JSON Schema. Empty means no input parameters. default: {} Choice: type: object properties: index: type: integer description: The index of this object in the choices array. message: $ref: '#/components/schemas/Message' finish_reason: type: string description: >- The reason why the model stopped generating. Three cases: stop (triggered by the stop parameter or natural stop), length (output too long), tool_calls (tool call required). logprobs: type: object nullable: true description: Token probability information output by the model. properties: content: type: array description: An array containing each Token and its log probability. items: description: Each Token and its log probability array element. type: object properties: token: type: string description: The text of the current Token. bytes: type: array description: >- The raw UTF‑8 byte list of the current Token, used to accurately restore output content (e.g. emojis or Chinese characters). items: type: integer logprob: type: number format: float description: >- The log probability of the current Token. A return value of null indicates very low probability. nullable: true top_logprobs: type: array description: >- The most likely candidate Tokens at the current Token position, the count is consistent with the request parameter top_logprobs. items: type: object description: Candidate Token and its log probability. properties: token: type: string description: Candidate Token text. bytes: type: array description: >- The raw UTF‑8 byte list of the current Token, used to accurately restore output content (e.g. emojis or Chinese characters). items: type: integer logprob: type: number format: float description: >- The log probability of this candidate Token. A return value of null indicates very low probability. nullable: true Usage: type: object properties: prompt_tokens: type: integer description: Number of input tokens. completion_tokens: type: integer description: Number of output tokens. total_tokens: type: integer description: Total tokens consumed, sum of prompt_tokens and completion_tokens. completion_tokens_details: type: object nullable: true description: Output token details. properties: audio_tokens: type: integer description: Number of output audio tokens. reasoning_tokens: type: integer description: Number of thinking process tokens. text_tokens: type: integer description: Number of output text tokens. prompt_tokens_details: type: object nullable: true properties: cached_tokens: type: integer description: >- The number of Tokens that hit the Cache. See Context Cache for details. text_tokens: type: integer description: The number of input text Tokens. image_tokens: type: integer description: The number of input image Tokens. video_tokens: type: integer description: The number of input video file or image list Tokens. audio_tokens: type: integer description: This parameter is currently fixed to null. cache_creation: type: object description: Explicit cache creation information. properties: ephemeral_5m_input_tokens: type: integer description: Tokens used to create explicit cache. cache_creation_input_tokens: type: integer description: Tokens used to create explicit cache. cache_type: type: string description: >- ephemeral when using explicit cache, otherwise this parameter does not exist. ChunkChoice: type: object properties: delta: $ref: '#/components/schemas/Delta' description: Incremental delta object. finish_reason: type: string nullable: true description: >- The reason why the model stopped generating. Four cases: stop (triggered by the stop parameter or natural stop), null (generation not finished), length (output too long), tool_calls (tool call required). index: type: integer description: Index in choices array. Use when n > 1. logprobs: $ref: '#/components/schemas/LogProbs' description: Probability information. ContentItem: type: object required: - type properties: type: type: string enum: - text - image_url - input_audio - video - video_url description: >- Set to text for text input; image_url for image input; input_audio for audio input; video for image-list video input; video_url for video file input. text: type: string description: Text content. Required when type=text. image_url: type: object description: Image information. Required when type=image_url. properties: url: type: string description: Image URL or Base64 Data URL. video_url: type: object description: Video file information. Required when type=video_url. properties: url: type: string description: Video file URL or Base64 Data URL. input_audio: type: object description: Audio information. Required when type=input_audio. properties: data: type: string description: Audio URL or Base64 Data URL. format: type: string description: Audio format, e.g., mp3, wav. video: type: array description: |- Image list for video. Required when type=video. Example value: [ "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/xzsgiz/football1.jpg", "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/tdescd/football2.jpg", "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/zefdja/football3.jpg", "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/aedbqh/football4.jpg" ] items: type: string cache_control: type: object description: Explicit cache control. properties: type: type: string enum: - ephemeral fps: type: number description: >- Frames per second for video extraction. Valid range [0.1, 10], default 2.0. For MiniMax/MiniMax-M3, range [0.2, 5], default 1. fps serves two purposes: 1. Controls frame extraction frequency when inputting a video file — one frame is extracted every 1/fps seconds. Applies to Qwen-VL, MiniMax/MiniMax-M3 and QVQ models. 2. Informs the model about the time interval between adjacent frames to better understand video temporal dynamics. Applies to both video files and image lists. Supported by Qwen3.7, Qwen3.6, Qwen3.5, Qwen3-VL, Qwen2.5-VL, Qwen3.5-Omni and QVQ models. Higher fps values are suitable for fast-moving scenes (e.g. sports, action movies), while lower values are suitable for long videos or static content. Example values: - Image list input: {"video":["https://xx1.jpg",...,"https://xxn.jpg"],"fps":2} - Video file input: {"video_url": {"url": "https://xx1.mp4"},"fps":2} min_pixels: type: integer description: >- Sets the minimum pixel threshold for input images or video frames. When the pixel count of an input image or video frame is below min_pixels, it will be scaled up until the total pixel count exceeds min_pixels. Applies to Qwen-VL and QVQ models. Value range: - For input images: Qwen3.7, Qwen3.6, Qwen3.5, Qwen3-VL have a default and minimum value of 65536. - For input video files or image lists: Qwen3.7, Qwen3.6, Qwen3.5, Qwen3.5-Omni, Qwen3-VL (commercial and open-source), qwen-vl-max, qwen-vl-max-0813, qwen-vl-plus, qwen-vl-plus-0815, qwen-vl-plus-0710 have a default of 65536 and a minimum of 4096. Example values: - Image input: {"type": "image_url","image_url": {"url":"https://xxxx.jpg"},"min_pixels": 65536} - Video file input: {"type": "video_url","video_url": {"url":"https://xxxx.mp4"},"min_pixels": 65536} - Image list input: {"type": "video","video": ["https://xx1.jpg",...,"https://xxn.jpg"],"min_pixels": 65536} max_pixels: type: integer description: >- Sets the maximum pixel threshold for input images or video frames. When the pixel count falls within [min_pixels, max_pixels], the model recognizes the original image as-is. When the pixel count exceeds max_pixels, the image is scaled down until the total pixel count falls below max_pixels. Applies to Qwen-VL and QVQ models. Value range: - For input images: - When vl_high_resolution_images is False: Qwen3.7, Qwen3.6, Qwen3.5, Qwen3-VL default to 2621440, maximum 16777216. - When vl_high_resolution_images is True: max_pixels is ignored for Qwen3.7, Qwen3.6, Qwen3.5-Omni, Qwen3.5, Qwen3-VL, qwen-vl-max, qwen-vl-max-0813, qwen-vl-plus, qwen-vl-plus-0815, qwen-vl-plus-0710; the maximum pixel count is fixed at 16777216. - For input video files or image lists: Qwen3.7, Qwen3.6, Qwen3.5 series, Qwen3.5-Omni, Qwen3-VL closed-source series, qwen3-vl-235b-a22b-thinking, qwen3-vl-235b-a22b-instruct default to 655360, maximum 2048000. Example values: - Image input: {"type": "image_url","image_url": {"url":"https://xxxx.jpg"},"max_pixels": 8388608} - Video file input: {"type": "video_url","video_url": {"url":"https://xxxx.mp4"},"max_pixels": 655360} - Image list input: {"type": "video","video": ["https://xx1.jpg",...,"https://xxn.jpg"],"max_pixels": 655360} total_pixels: type: integer description: >- Limits the total pixels of all frames extracted from a video (single-frame pixels × total frame count). If the total exceeds this limit, the system scales the frames while keeping each frame's pixel count within [min_pixels, max_pixels]. Applies to Qwen-VL and QVQ models. For long videos with many extracted frames, lowering this value can reduce token consumption and processing time, but may result in loss of image details. Value range: Qwen3.7, Qwen3.6 and Qwen3.5 series have a default and maximum of 819200000, corresponding to 800000 image tokens (each 32×32 pixels corresponds to 1 image token). Example values: - Video file input: {"type": "video_url","video_url": {"url":"https://xxxx.mp4"},"total_pixels": 134217728} - Image list input: {"type": "video","video": ["https://xx1.jpg",...,"https://xxn.jpg"],"total_pixels": 134217728} ToolCall: type: object required: - id - type - function - index description: Tool call information returned by the model after Function Calling. properties: id: type: string description: Tool response ID. type: type: string enum: - function description: Tool type. Currently only function. function: type: object required: - name - arguments description: Tool and input information. properties: name: type: string description: Tool name. arguments: type: string description: Function arguments in JSON format string. index: type: integer description: Index in the tool_calls array. Message: type: object required: - role properties: role: type: string enum: - system - user - assistant - tool description: >- The role of the message. Possible values: system, user, assistant, tool. content: anyOf: - type: string description: Text content. - type: array description: Multimodal content list (for image understanding). items: $ref: '#/components/schemas/ContentItem' description: >- Message content. System Message: content is string (system instruction). User Message: content is string (plain text) or array (multimodal content). Assistant Message: content is string (optional, can be empty when tool_calls present). Tool Message: content is string (tool function output, must be a string. If the tool returns structured data such as JSON, it must be serialized to a string). reasoning_content: type: string description: The model's chain of thought content. nullable: true refusal: type: string description: This parameter is currently fixed to null. nullable: true audio: type: object description: This parameter is currently fixed to null. nullable: true function_call: type: object description: >- This value is fixed to null. Please refer to the tool_calls parameter. nullable: true tool_calls: type: array description: >- After initiating Function Calling, the tool and input parameter information generated by the model. items: $ref: '#/components/schemas/ToolCall' partial: type: boolean description: >- Whether to enable prefix continuation. Only valid when role=assistant. Default: false. default: false tool_call_id: type: string description: >- ID returned after Function Calling, obtained via completion.choices[0].message.tool_calls[$index].id, used to associate Tool Message with the corresponding tool. Required only when role=tool. Delta: type: object description: Incremental message object in streaming. properties: content: type: string nullable: true description: Incremental message content. reasoning_content: type: string nullable: true description: Incremental thinking content. function_call: type: object nullable: true description: Default null. Refer to tool_calls. audio: type: object nullable: true description: Response when using Qwen-Omni model. refusal: type: object nullable: true description: Currently fixed to null. role: type: string description: Role. Only present in first chunk. tool_calls: type: array description: Tool call information after Function Calling. items: $ref: '#/components/schemas/ToolCallDelta' LogProbs: type: object nullable: true description: Probability information. properties: content: type: array description: Array of tokens with log probabilities. items: $ref: '#/components/schemas/LogProbContent' ToolCallDelta: type: object properties: index: type: integer description: Index in tool_calls array. id: type: string description: Unique identifier for this tool response. type: type: string enum: - function description: Tool type. Only function. function: type: object description: Tool information being called. properties: arguments: type: string description: >- Incremental input parameter information. All chunks' arguments concatenated form the complete input parameters. Due to model randomness, the output parameters may not conform to the function signature. Please validate parameter effectiveness before calling. name: type: string description: Tool name. Only in first chunk. LogProbContent: type: object properties: token: type: string description: Current token. bytes: type: array items: type: integer description: UTF-8 raw bytes. logprob: type: number format: float nullable: true description: Log probability. null means very low. top_logprobs: type: array description: Most likely tokens and log probabilities. items: $ref: '#/components/schemas/TopLogProb' TopLogProb: type: object properties: token: type: string description: Candidate token. bytes: type: array items: type: integer description: >- The raw UTF-8 byte list of the current Token, used to accurately restore output content (e.g. emojis or Chinese characters). logprob: type: number format: float nullable: true description: Log probability. null means very low. securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: JWT description: 'Pass Authorization: Bearer header.' ````