Create a chat completion using Doubao models. The content field accepts a plain string for text, or an array of content parts for multimodal input.
Multimodal content types: text, image_url, video_url.
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
The model to use.
doubao-seed-2.0-pro, doubao-seed-2.0-code, doubao-seed-2.0-lite, doubao-seed-2.0-mini, doubao-seed-1-8-251228, doubao-seed-1-6-flash-250828, doubao-seed-1-6-251015, doubao-seed-1-6-lite-251015, doubao-seed-1-6-vision-250815, glm-4-7-251222 "doubao-seed-1-6-251015"
Conversation messages. Each message has role and content.
Content array item types:
text: {"type": "text", "text": "..."}image_url: {"type": "image_url", "image_url": {"url": "https://..."}}video_url: {"type": "video_url", "video_url": {"url": "https://...", "fps": 2}}1[
{
"role": "user",
"content": [
{
"type": "image_url",
"image_url": {
"url": "https://ark-project.tos-cn-beijing.volces.com/doc_image/ark_demo_img_1.png"
}
},
{
"type": "text",
"text": "What is in this image?"
}
]
}
]
Maximum number of tokens to generate.
x >= 11024
Sampling temperature.
0 <= x <= 21
Nucleus sampling parameter.
0 <= x <= 1Whether to stream via SSE.
Up to 4 stop sequences.