Token360
注册

提交视频生成请求

POST/v1/videos

提交归一化的视频生成请求并创建异步任务。API 会根据 frame_images 与 input_references 的角色推断生成工作流。响应会返回视频任务 id；使用 GET /v1/videos/{video_id} 轮询该 id，即可查看生成状态并获取最终结果。

如需在任务进入终态时接收 Webhook，请提供可选的 callback_url 字段。投递行为、重试和回调载荷详见 Webhook。

可选字段和允许值因模型而异。发送 duration、resolution、size、aspect_ratio、generate_audio、service_tier 或 provider 策略字段等可选参数前，请先请求 GET /v1/models/{model_id}，并以该模型返回的 parameter_schema 和 supported_parameters 为准。

身份验证

Authorization Bearer

在 Authorization header 中使用 API key 作为 Bearer token。

Request Body

modelstringrequired

Model ID.

promptstringrequired

Video generation prompt.

durationinteger

Requested length of the generated video in seconds.

resolutionstring

Requested output video resolution or resolution tier.

sizestring

Requested output video size or resolution preset when the model uses a size field.

aspect_ratiostring

Requested output video frame shape as a width-to-height ratio.

generate_audioboolean

Controls whether video generation should include synthesized audio when supported.

prompt_extendboolean

Prompt extension flag.

watermarkboolean

Controls whether generated videos include a watermark when supported.

seedinteger

Optional numeric seed for repeatable generation when deterministic seeding is supported.

negative_promptstring

Negative prompt.

modestring

Generation mode.

cfg_scalenumber

Controls how strongly generation follows the prompt or guidance signal; higher values usually increase prompt adherence.

camera_controlobject

Camera control configuration.

camera_control.typestring

Camera control type.

camera_control.configobject

Camera control configuration.

camera_fixedboolean

Fixed camera flag.

callback_urlstring

Webhook callback URL.

external_task_idstring

External task ID.

character_orientationstring

Character orientation.

keep_original_soundboolean

Source-audio preservation flag.

qualitystring

Requested generation quality or fidelity tier.

fpsnumber

Requested output frame rate in frames per second.

sample_countinteger

Number of generated samples.

compression_qualitystring

Compression quality.

prompt_optimizerboolean

Prompt optimizer flag.

fast_pretreatmentboolean

Fast preprocessing flag.

return_last_frameboolean

Final-frame return flag.

movement_amplitudestring

Controls the amount of visual motion or camera/subject movement in the generated video when supported.

resize_modestring

Input resize mode.

person_generationstring

Person generation policy.

safety_identifierstring

Safety identifier.

draftboolean

Draft output flag.

request_idstring

Client request ID.

video_modestring

Video generation workflow.

service_tierstring

Service tier.

input_referencesarray

Reference media inputs.

input_references.typestringrequired

Reference media type, such as image_url, video_url, or audio_url.

input_references.image_urlobject

Image URL object for image references.

input_references.video_urlobject

Video URL object for video references.

input_references.audio_urlobject

Audio URL object for audio references.

input_references.rolestring

Reference role, such as reference, edit_source, or extend_source.

frame_imagesarray

Frame image inputs.

frame_images.typestringrequired

Frame media type, usually image_url.

frame_images.frame_typestringrequired

Frame role, such as first_frame or last_frame.

frame_images.image_urlobject

Image URL object for this frame.

bitrate_modestring

Requested bitrate or compression quality mode for generated video output.

metadataobject

Application metadata.

extra_bodyobject

Additional request body fields.

provider_optionsobject

Upstream configuration.

Response

idstring

视频任务 ID。

objectstring

固定为 video。

statusstring

任务状态。

modelstring

使用的模型。

promptstring

输入提示词。

created_atinteger

Unix 时间戳。

parametersobject

归一化后的任务参数。

contentobject

返回时包含的额外生成资产。

content.last_frame_urlstring

当 return_last_frame=true 且返回最后一帧时的图片 URL。

responseobject

可用时返回的原始响应详情。

errorobject

status=failed 时的错误详情。

error.messagestring

Human-readable error message.

error.codestring

Machine-readable error code.

error.typestring

Error category when returned.

error.stagestring

Processing stage where the error occurred.

error.upstream_http_statusinteger

Provider HTTP status when the error came from upstream.

error.upstream_messagestring

Provider error message when available.

usageobject

可用时返回的用量和计费详情。

usage.prompt_tokensinteger

Input token count when returned.

usage.completion_tokensinteger

Output token count when returned.

usage.total_tokensinteger

Total token count when returned.

usage.input_tokensinteger

Input token count for providers that use input/output names.

usage.output_tokensinteger

Output token count for providers that use input/output names.

usage.generated_imagesinteger

Generated image count when returned.

usage.audio_duration_secondsnumber

Audio duration used for billing when returned.

usage.video_duration_secondsnumber

Video duration used for billing when returned.

usage.provider_request_idstring

Provider request ID used for upstream correlation.

请求

Shell
1curl -X POST https://api.token360.ai/v1/videos \
2  -H "Authorization: Bearer sk-your-api-key" \
3  -H "Content-Type: application/json" \
4  -d '{
5    "model": "your-video-model",
6    "prompt": "A serene Japanese garden with cherry blossoms falling into a koi pond",
7    "resolution": "720p",
8    "duration": 8,
9    "aspect_ratio": "16:9",
10    "generate_audio": false,
11    "return_last_frame": false,
12    "execution_expires_after": 172800,
13    "safety_identifier": "user_123"
14  }'

响应

JSON
1{
2  "id": "your-video-id",
3  "object": "video",
4  "status": "queued",
5  "model": "your-video-model",
6  "prompt": "A serene Japanese garden with cherry blossoms falling into a koi pond",
7  "created_at": 1776351975,
8  "parameters": {
9    "resolution": "720p",
10    "duration": 8,
11    "aspect_ratio": "16:9",
12    "generate_audio": false,
13    "return_last_frame": false,
14    "execution_expires_after": 172800,
15    "safety_identifier": "user_123"
16  }
17}
此页面对您有帮助吗？