Description #

Provides deep reasoning capabilities for large models in multimodal scenarios. Uses models with deep reasoning abilities to analyze and interpret images, videos, or text, and returns structured text output. The operator automatically constructs a message structure compliant with multimodal model specifications. Users only need to provide image, video, or text data as specified to complete inference.

Key features #

• Deep reasoning mechanism: The model automatically decomposes questions and performs logical reasoning before answering, generating a reasoning chain (reasoning_content).
• Multimodal scenario support: Supports simultaneous input of images, videos, and text, and automatically assembles multimodal messages.
• Input simplification mechanism: Supports multiple data sources, including local files, HTTP/HTTPS URLs, TOS/S3 object storage, and more. Visual understanding capabilities can be enabled through simple configuration.
• Flexible reasoning mode: Supports controlling the deep reasoning mode via the thinking_type parameter (enabled / disabled / auto), allowing flexible trade-offs between answer quality and performance.

Input and output specifications #

• Input format:
  • Images (images): Supports string or list formats.
    • Supported data source types:
      • url: Network resource address. Supports http/https/tos/s3. TOS/S3 will automatically generate a pre-signed URL.
      • base64: Base64-encoded data.
      • binary: Binary data (internally converted to Base64 encoding).
  • Videos (videos): Supports string or list formats. Data source types are consistent with images.
  • Texts (texts): Supports string or list formats, used as user prompt input (do not mix string and list types in the same field).
• Output format:
  • Default mode: Returns a struct type containing the following fields:
    • llm_result: The model's final answer content.
    • reasoning_content: The model's reasoning chain / reasoning process.
  • When the environment variable LAS_LLM_FINISH_REASON_CHECK=true is set, the struct additionally includes:
    • finish_reason: The reason for the model result ending. Possible values include:
      • stop: Normal termination.
      • length: Exceeds token limit.
      • content_filter: Matches content filtering policy.
  • When the environment variable LAS_LLM_BOTS_REFERENCES=true is set, the struct additionally includes:
    • references: Retrieval results or external knowledge information referenced by the model, facilitating downstream transmission and parsing.

Model capability enhancement #

• Chain-of-thought visualization: The reasoning_content field outputs the model's reasoning process, making it easier to observe and review.
• Result reliability control: The finish_reason field identifies abnormal termination scenarios, such as length truncation or content filtering.
• Multimodal understanding: Supports mixed input parsing of images, videos, and text, suitable for complex multimodal scenarios.

Chat #

POST https://operator.las.ap-southeast-1.volces.com/api/v1/chat/completions

Interface description #

Invoke the doubao-seed-1.8 model for multimodal understanding.

Request parameters #

Response parameters #

Example #

Request example

curl --location "https://operator.las.ap-southeast-1.volces.com/api/v1/chat/completions" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $LAS_API_KEY" \
--data '{
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "video_url",
                    "video_url": {
                        "url": "https://las-ai-cn-beijing.tos-cn-beijing.volces.com/*****/sample.mp4"
                    }
                },
                {
                    "type": "text",
                    "text": "视频里面有什么"
                }
            ]
        }
    ],
    "model": "doubao-seed-1-8-251228"
}'

Response example

{
    "id": "021768911071736e97fe2f517eced7c4391200710ba13b1ae8bec",
    "object": "chat.completion",
    "created": 1768911086,
    "model": "doubao-seed-1-8-32k-251228",
    "serviceTier": "default",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "视频呈现了这样的内容：\n一位戴着浅色宽边遮阳帽、墨镜，身穿白色上衣搭配花色长裙的女士，坐在白色斑驳建筑旁的黑色折叠椅上，一边演奏手风琴，一边投入地演唱。她身旁地面放着一瓶水，背景是开阔的蓝色水域，远处可见绿植覆盖的陆地，场景位于海边区域。视频中镜头有移动拉近，展现演奏的细节，后期还有穿绿色上衣、卡其色下装的行人从画面右侧路过。",
                "name": null,
                "reasoning_content": "用户现在需要总结视频里的内容。首先看视频：一位女士戴着浅色宽边帽、墨镜，白色上衣花裙子，坐在白色建筑旁的折叠椅上，演奏手风琴，同时还在唱歌。背景是海边，有蓝色水域和远处的陆地。镜头有移动，后来有行人（绿上衣卡其裤等）从旁边走过。需要把这些元素整理出来：\n\n视频中，一位戴着浅色宽边遮阳帽、墨镜，身穿白色上衣和花色长裙的女士，坐在白色建筑（墙面有斑驳痕迹）旁的黑色折叠椅上，一边演奏手风琴，一边演唱。她身旁放着一瓶水，背景是开阔的蓝色水域与远处的绿植覆盖的陆地，环境是海边区域。过程中镜头有调整，拉近展现演奏细节，还有行人（穿绿色上衣、卡其色下装的人）从画面右侧走过。",
                "function_call": null,
                "tool_calls": null,
                "tool_call_id": null
            },
            "finish_reason": "stop",
            "moderation_hit_type": null,
            "logprobs": null
        }
    ],
    "usage": {
        "prompt_tokens": 3930,
        "completion_tokens": 294,
        "total_tokens": 4224,
        "prompt_tokens_details": {
            "cached_tokens": 0,
            "provisioned_tokens": null
        },
        "completion_tokens_details": {
            "reasoning_tokens": 189,
            "provisioned_tokens": null
        }
    }
}

Responses #

Interface description #

Use the Responses interface to invoke the doubao-seed-1.8 model for multimodal understanding. Refer to Create a model response for interface definition.
Supported models and versions: doubao-seed-1-8-251228.

Example #

Request example

curl --location "https://operator.las.ap-southeast-1.volces.com/api/v1/responses" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $LAS_API_KEY" \
--data '{
    "input": [
        {
            "role": "user",
            "content": [
                {
                    "type": "input_video",
                    "video_url":  "https://las-ai-cn-beijing.tos-cn-beijing.volces.com/*****/sample.mp4"
                },
                {
                    "type": "input_text",
                    "text": "视频里面有什么"
                }
            ]
        }
    ],
    "model": "doubao-seed-1-8-251228"
}'

Response example

{
    "created_at": 1772617764,
    "error": null,
    "id": "resp_021772617762470960a4483e1c6480e5dcf931407efe2bda06a32",
    "incomplete_details": null,
    "max_output_tokens": 32768,
    "model": "doubao-seed-1-8-251228",
    "object": "response",
    "output": [
        {
            "type": "reasoning",
            "id": "rs_02177261776458300000000000000000000ffffac1504e228c011",
            "summary": [
                {
                    "type": "summary_text",
                    "text": "用户现在需要分析视频内容，先看画面：一位戴着浅色宽边帽、墨镜，穿白色上衣和花裙子的女士，坐在白色建筑旁的折叠椅上，演奏手风琴，同时还在唱歌。背景是海边，有蓝色的水域和远处的陆地。视频里还有其他元素：她旁边有水瓶，后来有行人（穿绿上衣、卡其裤的人，还有另一个人）从她旁边走过。整个场景是户外海边，女士专注地演奏手风琴并演唱，动作包括按手风琴的键、推拉风箱，头部随着音乐摆动。现在整理这些元素，清晰描述出来。"
                }
            ],
            "status": "completed"
        },
        {
            "type": "message",
            "id": "msg_02177261776828500000000000000000000ffffac1504e2a4e276",
            "role": "assistant",
            "content": [
                {
                    "type": "output_text",
                    "text": "视频里呈现的内容有：\n1. 人物与行为：一位戴着浅色宽边遮阳帽、墨镜，身穿白色上衣+花卉图案长裙的女士，坐在白色建筑旁的折叠椅上，一边演奏手风琴（手部按动琴键、推拉风箱），一边开口演唱，头部也会随着音乐律动；后期有两位行人（一位穿湖绿色上衣+卡其色下装、一位穿白色上衣）从她身旁路过。\n2. 环境与物品：场景是户外海边区域，背景能看到蓝色的水域与远处的绿植陆地；女士身旁地面放着一瓶矿泉水，她身后有打开的箱子。",
                    "annotations": null
                }
            ],
            "status": "completed",
            "partial": null
        }
    ],
    "previous_response_id": null,
    "thinking": null,
    "reasoning": null,
    "service_tier": "default",
    "status": "completed",
    "temperature": null,
    "tools": null,
    "top_p": null,
    "usage": {
        "input_tokens": 3930,
        "output_tokens": 276,
        "total_tokens": 4206,
        "input_tokens_details": {
            "cached_tokens": 0
        },
        "output_tokens_details": {
            "reasoning_tokens": 137
        },
        "tool_usage": null,
        "tool_usage_details": null
    },
    "caching": {
        "type": "disabled",
        "prefix": null
    },
    "text": null,
    "instructions": null,
    "store": true,
    "expire_at": 1772876962,
    "tool_choice": null,
    "parallel_tool_calls": null,
    "max_tool_calls": null
}

Error codes #