Skip to content
SeaCloud Docs
Home

Model Invocation Examples

This page lists complete invocation information for the multimodal queue API by model ID. All models use /v1/queue/{endpoint}. The request body is the model parameter object itself and does not need an input wrapper.

Request steps

Section titled “Request steps”

Every model uses the same invocation steps. Only replace ENDPOINT and the request-body fields.

Terminal window
export BASE_URL="https://cloud.seaart.ai/model"
export API_KEY="YOUR_API_KEY"
export ENDPOINT="nano_banana_2"


COMMON_HEADERS=(
  -H "Authorization: Key ${API_KEY}"
  -H "Content-Type: application/json"
)


SUBMIT_RESPONSE="$(curl -sS -X POST "${BASE_URL}/v1/queue/${ENDPOINT}" \
  "${COMMON_HEADERS[@]}" \
  -d '{
    "prompt": "a cinematic photo of a cat astronaut"
  }')"


REQUEST_ID="$(echo "${SUBMIT_RESPONSE}" | jq -r '.request_id')"
STATUS_URL="$(echo "${SUBMIT_RESPONSE}" | jq -r '.status_url')"
RESPONSE_URL="$(echo "${SUBMIT_RESPONSE}" | jq -r '.response_url')"


while true; do
  STATUS_RESPONSE="$(curl -sS "${STATUS_URL}" "${COMMON_HEADERS[@]}")"
  STATUS="$(echo "${STATUS_RESPONSE}" | jq -r '.status')"
  ERROR="$(echo "${STATUS_RESPONSE}" | jq -r '.error // empty')"


  if [ "${STATUS}" = "COMPLETED" ]; then
    if [ -n "${ERROR}" ]; then
      echo "task failed: ${ERROR}"
      exit 1
    fi
    break
  fi


  sleep 3
done


curl -sS "${RESPONSE_URL}" "${COMMON_HEADERS[@]}" | jq .

Unified response structure

Section titled “Unified response structure”

After a task succeeds, the result endpoint always returns request_id, outputs, and metadata. Multiple result URLs are returned as multiple outputs records in order.

{
  "request_id": "mmsu_01hxyz...",
  "outputs": [
    {
      "type": "image",
      "url": "https://example.com/output.png",
      "content_type": "image/png",
      "file_name": "output.png",
      "width": 1024,
      "height": 1024
    }
  ],
  "metadata": {
    "prompt": "a cinematic photo of a cat astronaut"
  }
}

Supported models

Image, 22 total

wan25_i2i_previewwan25_i2i_preview_intlwan26_image_intlwan27_imagewan27_image_promidjourney_diffusionwan26_i2iqwen_image_edit_plusgpt_image_2gpt_image_2_editgpt_image_1_editgpt_image_1_5gpt_image_1_5_editgpt_image_1flux_pro_11flux_kontext_proflux_kontext_maxflux_2_maxflux_2_pronano_banana_2nano_banana_pronano_banana

Video, 13 total

happyhorse_1.0_i2vminimax_hailuo_23_i2vminimax_hailuo_02_i2vminimax_hailuo_23_fast_i2vtencent_mps_super_resolutionpixverse_v6_i2vminimax_i2v_01_directorminimax_i2v_01_liveminimax_i2v_01wan22_i2v_flashwan22_i2v_pluswan25_t2v_previewwan26_i2v

Audio, 10 total

minimax_speech_28_hdminimax_speech_28_turbominimax_speech_26_hdminimax_speech_26_turbominimax_speech_02_hdminimax_speech_02_turbominimax_speech_01_hdminimax_speech_01_turbomureka_lyrics_generatormureka_song_generator

3D, 3 total

tencent_hunyuan_3dtencent_hunyuan_3d_protencent_hunyuan_3d_rapid

Model parameter matrix

The table below lists request paths, full parameter lists, copyable request-body examples, and successful response structures by model ID. Fields marked required must be provided; undeclared fields are rejected.

Model ID Request path Request-body parameters Request-body example Success response shape
wan25_i2i_preview
Image 
POST /v1/queue/wan25_i2i_preview
GET  /v1/queue/wan25_i2i_preview/requests/{request_id}/status
GET  /v1/queue/wan25_i2i_preview/requests/{request_id}/response
prompt string, required images string[], required negative_prompt string, optional n int, optional watermark bool, optional seed int, optional 
{
  "prompt": "turn the input image into a clean studio product shot",
  "images": [
    "https://example.com/input.png"
  ]
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
wan25_i2i_preview_intl
Image 
POST /v1/queue/wan25_i2i_preview_intl
GET  /v1/queue/wan25_i2i_preview_intl/requests/{request_id}/status
GET  /v1/queue/wan25_i2i_preview_intl/requests/{request_id}/response
prompt string, required images string[], required negative_prompt string, optional n int, optional watermark bool, optional seed int, optional 
{
  "prompt": "turn the input image into a clean studio product shot",
  "images": [
    "https://example.com/input.png"
  ]
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
wan26_image_intl
Image 
POST /v1/queue/wan26_image_intl
GET  /v1/queue/wan26_image_intl/requests/{request_id}/status
GET  /v1/queue/wan26_image_intl/requests/{request_id}/response
role string, optional , default user prompt string, required image string, optional image_url string, optional image_2 string, optional image_3 string, optional image_4 string, optional enable_interleave bool, optional , default true negative_prompt string, optional size string, optional n int, optional prompt_extend bool, optional watermark bool, optional seed int, optional 
{
  "prompt": "a cinematic photo of a cat astronaut"
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
wan27_image
Image 
POST /v1/queue/wan27_image
GET  /v1/queue/wan27_image/requests/{request_id}/status
GET  /v1/queue/wan27_image/requests/{request_id}/response
role string, optional , default user prompt string, required negative_prompt string, optional size string, optional n int, optional prompt_extend bool, optional watermark bool, optional seed int, optional 
{
  "prompt": "a cinematic photo of a cat astronaut"
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
wan27_image_pro
Image 
POST /v1/queue/wan27_image_pro
GET  /v1/queue/wan27_image_pro/requests/{request_id}/status
GET  /v1/queue/wan27_image_pro/requests/{request_id}/response
role string, optional , default user prompt string, required negative_prompt string, optional size string, optional n int, optional prompt_extend bool, optional watermark bool, optional seed int, optional 
{
  "prompt": "a cinematic photo of a cat astronaut"
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
midjourney_diffusion
Image 
POST /v1/queue/midjourney_diffusion
GET  /v1/queue/midjourney_diffusion/requests/{request_id}/status
GET  /v1/queue/midjourney_diffusion/requests/{request_id}/response
text string, required 
{
  "text": "a cinematic photo of a cat astronaut"
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
wan26_i2i
Image 
POST /v1/queue/wan26_i2i
GET  /v1/queue/wan26_i2i/requests/{request_id}/status
GET  /v1/queue/wan26_i2i/requests/{request_id}/response
prompt string, required images string[], required negative_prompt string, optional size string, optional enable_interleave bool, optional n int, optional max_images int, optional prompt_extend bool, optional watermark bool, optional seed int, optional 
{
  "prompt": "turn the input image into a clean studio product shot",
  "images": [
    "https://example.com/input.png"
  ]
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
qwen_image_edit_plus
Image 
POST /v1/queue/qwen_image_edit_plus
GET  /v1/queue/qwen_image_edit_plus/requests/{request_id}/status
GET  /v1/queue/qwen_image_edit_plus/requests/{request_id}/response
prompt string, required images string[], required negative_prompt string, optional size string, optional enable_interleave bool, optional n int, optional max_images int, optional prompt_extend bool, optional watermark bool, optional seed int, optional 
{
  "prompt": "turn the input image into a clean studio product shot",
  "images": [
    "https://example.com/input.png"
  ]
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
gpt_image_2
Image 
POST /v1/queue/gpt_image_2
GET  /v1/queue/gpt_image_2/requests/{request_id}/status
GET  /v1/queue/gpt_image_2/requests/{request_id}/response
prompt string, required n int, optional size string, optional quality string, optional background string, optional output_format string, optional output_compression int, optional moderation string, optional user string, optional 
{
  "prompt": "a cinematic photo of a cat astronaut"
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
gpt_image_2_edit
Image 
POST /v1/queue/gpt_image_2_edit
GET  /v1/queue/gpt_image_2_edit/requests/{request_id}/status
GET  /v1/queue/gpt_image_2_edit/requests/{request_id}/response
prompt string, required image any, required mask any, optional n int, optional size string, optional quality string, optional background string, optional output_format string, optional output_compression int, optional response_format string, optional user string, optional watermark bool, optional 
{
  "prompt": "turn the input image into a clean studio product shot",
  "image": [
    "https://example.com/input.png"
  ]
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
gpt_image_1_edit
Image 
POST /v1/queue/gpt_image_1_edit
GET  /v1/queue/gpt_image_1_edit/requests/{request_id}/status
GET  /v1/queue/gpt_image_1_edit/requests/{request_id}/response
prompt string, required image any, required mask any, optional n int, optional size string, optional quality string, optional background string, optional output_format string, optional output_compression int, optional response_format string, optional user string, optional 
{
  "prompt": "turn the input image into a clean studio product shot",
  "image": [
    "https://example.com/input.png"
  ]
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
gpt_image_1_5
Image 
POST /v1/queue/gpt_image_1_5
GET  /v1/queue/gpt_image_1_5/requests/{request_id}/status
GET  /v1/queue/gpt_image_1_5/requests/{request_id}/response
prompt string, required n int, optional size string, optional quality string, optional output_format string, optional output_compression int, optional user string, optional 
{
  "prompt": "a cinematic photo of a cat astronaut"
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
gpt_image_1_5_edit
Image 
POST /v1/queue/gpt_image_1_5_edit
GET  /v1/queue/gpt_image_1_5_edit/requests/{request_id}/status
GET  /v1/queue/gpt_image_1_5_edit/requests/{request_id}/response
prompt string, required image any, required mask any, optional background string, optional input_fidelity string, optional n int, optional output_compression int, optional output_format string, optional partial_images int, optional quality string, optional size string, optional stream bool, optional user string, optional 
{
  "prompt": "turn the input image into a clean studio product shot",
  "image": [
    "https://example.com/input.png"
  ]
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
gpt_image_1
Image 
POST /v1/queue/gpt_image_1
GET  /v1/queue/gpt_image_1/requests/{request_id}/status
GET  /v1/queue/gpt_image_1/requests/{request_id}/response
prompt string, required n int, optional size string, optional quality string, optional background string, optional output_format string, optional output_compression int, optional moderation string, optional user string, optional 
{
  "prompt": "a cinematic photo of a cat astronaut"
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
flux_pro_11
Image 
POST /v1/queue/flux_pro_11
GET  /v1/queue/flux_pro_11/requests/{request_id}/status
GET  /v1/queue/flux_pro_11/requests/{request_id}/response
prompt string, required image_prompt string, optional width int, optional height int, optional prompt_upsampling bool, optional seed int, optional safety_tolerance int, optional output_format string, optional 
{
  "prompt": "a cinematic photo of a cat astronaut"
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
flux_kontext_pro
Image 
POST /v1/queue/flux_kontext_pro
GET  /v1/queue/flux_kontext_pro/requests/{request_id}/status
GET  /v1/queue/flux_kontext_pro/requests/{request_id}/response
prompt string, required input_image string, optional input_image_2 string, optional input_image_3 string, optional input_image_4 string, optional seed int, optional aspect_ratio string, optional output_format string, optional prompt_upsampling bool, optional safety_tolerance any, optional 
{
  "prompt": "turn the input image into a clean studio product shot",
  "input_image": "https://example.com/input.png"
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
flux_kontext_max
Image 
POST /v1/queue/flux_kontext_max
GET  /v1/queue/flux_kontext_max/requests/{request_id}/status
GET  /v1/queue/flux_kontext_max/requests/{request_id}/response
prompt string, required input_image string, optional input_image_2 string, optional input_image_3 string, optional input_image_4 string, optional image any, optional seed int, optional aspect_ratio string, optional steps int, optional guidance_scale number, optional negative_prompt string, optional output_format string, optional prompt_upsampling bool, optional safety_tolerance int, optional n int, optional quality string, optional size string, optional 
{
  "prompt": "turn the input image into a clean studio product shot",
  "input_image": "https://example.com/input.png"
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
flux_2_max
Image 
POST /v1/queue/flux_2_max
GET  /v1/queue/flux_2_max/requests/{request_id}/status
GET  /v1/queue/flux_2_max/requests/{request_id}/response
prompt string, required image_urls string[], optional seed int, optional width int, optional height int, optional safety_tolerance int, optional output_format string, optional 
{
  "prompt": "a cinematic photo of a cat astronaut"
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
flux_2_pro
Image 
POST /v1/queue/flux_2_pro
GET  /v1/queue/flux_2_pro/requests/{request_id}/status
GET  /v1/queue/flux_2_pro/requests/{request_id}/response
prompt string, required input_image string, optional image_urls string[], optional seed int, optional width int, optional height int, optional safety_tolerance int, optional output_format string, optional guidance_scale number, optional num_inference_steps int, optional 
{
  "prompt": "a cinematic photo of a cat astronaut",
  "input_image": "https://example.com/input.png"
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
nano_banana_2
Image 
POST /v1/queue/nano_banana_2
GET  /v1/queue/nano_banana_2/requests/{request_id}/status
GET  /v1/queue/nano_banana_2/requests/{request_id}/response
prompt string, required image_urls string[], optional aspect_ratio string, optional image_size string, optional resolution string, optional response_modalities string[], optional watermark bool, optional reference_image_urls string[], optional reference_items array, optional quality string, optional n int, optional 
{
  "prompt": "a cinematic photo of a cat astronaut"
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
nano_banana_pro
Image 
POST /v1/queue/nano_banana_pro
GET  /v1/queue/nano_banana_pro/requests/{request_id}/status
GET  /v1/queue/nano_banana_pro/requests/{request_id}/response
prompt string, required image_urls string[], optional aspect_ratio string, optional image_size string, optional resolution string, optional response_modalities string[], optional watermark bool, optional moderation bool, optional quality string, optional n int, optional 
{
  "prompt": "a cinematic photo of a cat astronaut"
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
nano_banana
Image 
POST /v1/queue/nano_banana
GET  /v1/queue/nano_banana/requests/{request_id}/status
GET  /v1/queue/nano_banana/requests/{request_id}/response
prompt string, required image_urls string[], optional aspect_ratio string, optional image_size string, optional resolution string, optional response_modalities string[], optional watermark bool, optional moderation bool, optional n int, optional 
{
  "prompt": "a cinematic photo of a cat astronaut"
}
 {request_id, outputs:[{type:"image", url, content_type, file_name, width, height, metadata?}], metadata}
happyhorse_1.0_i2v
Video 
POST /v1/queue/happyhorse_1.0_i2v
GET  /v1/queue/happyhorse_1.0_i2v/requests/{request_id}/status
GET  /v1/queue/happyhorse_1.0_i2v/requests/{request_id}/response
prompt string, required media any, required duration int, optional resolution string, optional prompt_extend bool, optional seed int, optional watermark bool, optional 
{
  "prompt": "camera slowly pushes in, warm sunset light, cinematic motion",
  "media": "https://example.com/first-frame.jpg"
}
 {request_id, outputs:[{type:"video", url, content_type, file_name, file_size, duration, metadata?}], metadata}
minimax_hailuo_23_i2v
Video 
POST /v1/queue/minimax_hailuo_23_i2v
GET  /v1/queue/minimax_hailuo_23_i2v/requests/{request_id}/status
GET  /v1/queue/minimax_hailuo_23_i2v/requests/{request_id}/response
first_frame_image string, required prompt string, optional duration int, optional resolution string, optional prompt_optimizer bool, optional fast_pretreatment bool, optional 
{
  "first_frame_image": "https://example.com/input.png",
  "prompt": "camera slowly pushes in, warm sunset light, cinematic motion"
}
 {request_id, outputs:[{type:"video", url, content_type, file_name, file_size, duration, metadata?}], metadata}
minimax_hailuo_02_i2v
Video 
POST /v1/queue/minimax_hailuo_02_i2v
GET  /v1/queue/minimax_hailuo_02_i2v/requests/{request_id}/status
GET  /v1/queue/minimax_hailuo_02_i2v/requests/{request_id}/response
first_frame_image string, required prompt string, optional duration int, optional resolution string, optional prompt_optimizer bool, optional fast_pretreatment bool, optional 
{
  "first_frame_image": "https://example.com/input.png",
  "prompt": "camera slowly pushes in, warm sunset light, cinematic motion"
}
 {request_id, outputs:[{type:"video", url, content_type, file_name, file_size, duration, metadata?}], metadata}
minimax_hailuo_23_fast_i2v
Video 
POST /v1/queue/minimax_hailuo_23_fast_i2v
GET  /v1/queue/minimax_hailuo_23_fast_i2v/requests/{request_id}/status
GET  /v1/queue/minimax_hailuo_23_fast_i2v/requests/{request_id}/response
first_frame_image string, required prompt string, optional duration int, optional resolution string, optional prompt_optimizer bool, optional fast_pretreatment bool, optional 
{
  "first_frame_image": "https://example.com/input.png",
  "prompt": "camera slowly pushes in, warm sunset light, cinematic motion"
}
 {request_id, outputs:[{type:"video", url, content_type, file_name, file_size, duration, metadata?}], metadata}
tencent_mps_super_resolution
Video 
POST /v1/queue/tencent_mps_super_resolution
GET  /v1/queue/tencent_mps_super_resolution/requests/{request_id}/status
GET  /v1/queue/tencent_mps_super_resolution/requests/{request_id}/response
input_url string, required input_type string, optional , default URL output_bucket string, optional , default top-rank-cos-1350346443 output_region string, optional , default na-siliconvalley output_storage_type string, optional , default COS output_dir string, optional , default /super_resolution definition any, optional , default 1560242 short int, optional session_id string, optional session_context string, optional task_notify_config object, optional task_priority int, optional 
{
  "input_url": "https://example.com/source-video.mp4"
}
 {request_id, outputs:[{type:"video", url, content_type, file_name, file_size, duration, metadata?}], metadata}
pixverse_v6_i2v
Video 
POST /v1/queue/pixverse_v6_i2v
GET  /v1/queue/pixverse_v6_i2v/requests/{request_id}/status
GET  /v1/queue/pixverse_v6_i2v/requests/{request_id}/response
image string, required img_id string, optional prompt string, optional negative_prompt string, optional duration number, optional quality string, optional seed int, optional style string, optional template_id int, optional sound_effect_switch bool, optional sound_effect_content string, optional lip_sync_switch bool, optional lip_sync_tts_content string, optional lip_sync_tts_speaker_id string, optional generate_audio_switch bool, optional generate_multi_clip_switch bool, optional thinking_type string, optional 
{
  "image": "https://example.com/input.png",
  "prompt": "camera slowly pushes in, warm sunset light, cinematic motion"
}
 {request_id, outputs:[{type:"video", url, content_type, file_name, file_size, duration, metadata?}], metadata}
minimax_i2v_01_director
Video 
POST /v1/queue/minimax_i2v_01_director
GET  /v1/queue/minimax_i2v_01_director/requests/{request_id}/status
GET  /v1/queue/minimax_i2v_01_director/requests/{request_id}/response
first_frame_image string, required prompt string, optional prompt_optimizer bool, optional 
{
  "first_frame_image": "https://example.com/input.png",
  "prompt": "camera slowly pushes in, warm sunset light, cinematic motion"
}
 {request_id, outputs:[{type:"video", url, content_type, file_name, file_size, duration, metadata?}], metadata}
minimax_i2v_01_live
Video 
POST /v1/queue/minimax_i2v_01_live
GET  /v1/queue/minimax_i2v_01_live/requests/{request_id}/status
GET  /v1/queue/minimax_i2v_01_live/requests/{request_id}/response
first_frame_image string, required prompt string, optional duration int, optional resolution string, optional prompt_optimizer bool, optional 
{
  "first_frame_image": "https://example.com/input.png",
  "prompt": "camera slowly pushes in, warm sunset light, cinematic motion"
}
 {request_id, outputs:[{type:"video", url, content_type, file_name, file_size, duration, metadata?}], metadata}
minimax_i2v_01
Video 
POST /v1/queue/minimax_i2v_01
GET  /v1/queue/minimax_i2v_01/requests/{request_id}/status
GET  /v1/queue/minimax_i2v_01/requests/{request_id}/response
first_frame_image string, required prompt string, optional duration int, optional resolution string, optional prompt_optimizer bool, optional 
{
  "first_frame_image": "https://example.com/input.png",
  "prompt": "camera slowly pushes in, warm sunset light, cinematic motion"
}
 {request_id, outputs:[{type:"video", url, content_type, file_name, file_size, duration, metadata?}], metadata}
wan22_i2v_flash
Video 
POST /v1/queue/wan22_i2v_flash
GET  /v1/queue/wan22_i2v_flash/requests/{request_id}/status
GET  /v1/queue/wan22_i2v_flash/requests/{request_id}/response
prompt string, required img_url string, required duration int, optional resolution string, optional prompt_extend bool, optional seed int, optional watermark bool, optional 
{
  "prompt": "camera slowly pushes in, warm sunset light, cinematic motion",
  "img_url": "https://example.com/input.png"
}
 {request_id, outputs:[{type:"video", url, content_type, file_name, file_size, duration, metadata?}], metadata}
wan22_i2v_plus
Video 
POST /v1/queue/wan22_i2v_plus
GET  /v1/queue/wan22_i2v_plus/requests/{request_id}/status
GET  /v1/queue/wan22_i2v_plus/requests/{request_id}/response
prompt string, required img_url string, required duration int, optional resolution string, optional prompt_extend bool, optional seed int, optional watermark bool, optional 
{
  "prompt": "camera slowly pushes in, warm sunset light, cinematic motion",
  "img_url": "https://example.com/input.png"
}
 {request_id, outputs:[{type:"video", url, content_type, file_name, file_size, duration, metadata?}], metadata}
wan25_t2v_preview
Video 
POST /v1/queue/wan25_t2v_preview
GET  /v1/queue/wan25_t2v_preview/requests/{request_id}/status
GET  /v1/queue/wan25_t2v_preview/requests/{request_id}/response
prompt string, required duration int, optional resolution string, optional prompt_extend bool, optional seed int, optional watermark bool, optional 
{
  "prompt": "camera slowly pushes in, warm sunset light, cinematic motion"
}
 {request_id, outputs:[{type:"video", url, content_type, file_name, file_size, duration, metadata?}], metadata}
wan26_i2v
Video 
POST /v1/queue/wan26_i2v
GET  /v1/queue/wan26_i2v/requests/{request_id}/status
GET  /v1/queue/wan26_i2v/requests/{request_id}/response
prompt string, required img_url string, required duration int, optional resolution string, optional prompt_extend bool, optional seed int, optional watermark bool, optional 
{
  "prompt": "camera slowly pushes in, warm sunset light, cinematic motion",
  "img_url": "https://example.com/input.png"
}
 {request_id, outputs:[{type:"video", url, content_type, file_name, file_size, duration, metadata?}], metadata}
minimax_speech_28_hd
Audio 
POST /v1/queue/minimax_speech_28_hd
GET  /v1/queue/minimax_speech_28_hd/requests/{request_id}/status
GET  /v1/queue/minimax_speech_28_hd/requests/{request_id}/response
text string, required stream bool, optional output_format string, optional voice_setting object, optional audio_setting object, optional language_boost string, optional pronunciation_dict object, optional voice_modify object, optional subtitle_enable bool, optional stream_options object, optional aigc_watermark bool, optional 
{
  "text": "你好，欢迎使用 SeaCloud 多模态模型 API。",
  "stream": false,
  "output_format": "url",
  "voice_setting": {
    "voice_id": "female-shaonv",
    "speed": 1.08,
    "vol": 1,
    "pitch": 0
  },
  "audio_setting": {
    "sample_rate": 32000,
    "bitrate": 128000,
    "channel": 1,
    "format": "mp3"
  },
  "language_boost": "Chinese",
  "aigc_watermark": false
}
 {request_id, outputs:[{type:"audio", url, content_type, file_name, file_size, duration, metadata?}], metadata}
minimax_speech_28_turbo
Audio 
POST /v1/queue/minimax_speech_28_turbo
GET  /v1/queue/minimax_speech_28_turbo/requests/{request_id}/status
GET  /v1/queue/minimax_speech_28_turbo/requests/{request_id}/response
text string, required stream bool, optional output_format string, optional voice_setting object, optional audio_setting object, optional language_boost string, optional pronunciation_dict object, optional voice_modify object, optional subtitle_enable bool, optional stream_options object, optional aigc_watermark bool, optional 
{
  "text": "你好，欢迎使用 SeaCloud 多模态模型 API。",
  "stream": false,
  "output_format": "url",
  "voice_setting": {
    "voice_id": "female-shaonv",
    "speed": 1.08,
    "vol": 1,
    "pitch": 0
  },
  "audio_setting": {
    "sample_rate": 32000,
    "bitrate": 128000,
    "channel": 1,
    "format": "mp3"
  },
  "language_boost": "Chinese",
  "aigc_watermark": false
}
 {request_id, outputs:[{type:"audio", url, content_type, file_name, file_size, duration, metadata?}], metadata}
minimax_speech_26_hd
Audio 
POST /v1/queue/minimax_speech_26_hd
GET  /v1/queue/minimax_speech_26_hd/requests/{request_id}/status
GET  /v1/queue/minimax_speech_26_hd/requests/{request_id}/response
text string, required stream bool, optional output_format string, optional voice_setting object, optional audio_setting object, optional language_boost string, optional pronunciation_dict object, optional voice_modify object, optional subtitle_enable bool, optional stream_options object, optional aigc_watermark bool, optional 
{
  "text": "你好，欢迎使用 SeaCloud 多模态模型 API。",
  "stream": false,
  "output_format": "url",
  "voice_setting": {
    "voice_id": "female-shaonv",
    "speed": 1.08,
    "vol": 1,
    "pitch": 0
  },
  "audio_setting": {
    "sample_rate": 32000,
    "bitrate": 128000,
    "channel": 1,
    "format": "mp3"
  },
  "language_boost": "Chinese",
  "aigc_watermark": false
}
 {request_id, outputs:[{type:"audio", url, content_type, file_name, file_size, duration, metadata?}], metadata}
minimax_speech_26_turbo
Audio 
POST /v1/queue/minimax_speech_26_turbo
GET  /v1/queue/minimax_speech_26_turbo/requests/{request_id}/status
GET  /v1/queue/minimax_speech_26_turbo/requests/{request_id}/response
text string, required stream bool, optional output_format string, optional voice_setting object, optional audio_setting object, optional language_boost string, optional pronunciation_dict object, optional voice_modify object, optional subtitle_enable bool, optional stream_options object, optional aigc_watermark bool, optional 
{
  "text": "你好，欢迎使用 SeaCloud 多模态模型 API。",
  "stream": false,
  "output_format": "url",
  "voice_setting": {
    "voice_id": "female-shaonv",
    "speed": 1.08,
    "vol": 1,
    "pitch": 0
  },
  "audio_setting": {
    "sample_rate": 32000,
    "bitrate": 128000,
    "channel": 1,
    "format": "mp3"
  },
  "language_boost": "Chinese",
  "aigc_watermark": false
}
 {request_id, outputs:[{type:"audio", url, content_type, file_name, file_size, duration, metadata?}], metadata}
minimax_speech_02_hd
Audio 
POST /v1/queue/minimax_speech_02_hd
GET  /v1/queue/minimax_speech_02_hd/requests/{request_id}/status
GET  /v1/queue/minimax_speech_02_hd/requests/{request_id}/response
text string, required stream bool, optional output_format string, optional voice_setting object, optional audio_setting object, optional language_boost string, optional pronunciation_dict object, optional voice_modify object, optional subtitle_enable bool, optional stream_options object, optional aigc_watermark bool, optional 
{
  "text": "你好，欢迎使用 SeaCloud 多模态模型 API。",
  "stream": false,
  "output_format": "url",
  "voice_setting": {
    "voice_id": "female-shaonv",
    "speed": 1.08,
    "vol": 1,
    "pitch": 0
  },
  "audio_setting": {
    "sample_rate": 32000,
    "bitrate": 128000,
    "channel": 1,
    "format": "mp3"
  },
  "language_boost": "Chinese",
  "aigc_watermark": false
}
 {request_id, outputs:[{type:"audio", url, content_type, file_name, file_size, duration, metadata?}], metadata}
minimax_speech_02_turbo
Audio 
POST /v1/queue/minimax_speech_02_turbo
GET  /v1/queue/minimax_speech_02_turbo/requests/{request_id}/status
GET  /v1/queue/minimax_speech_02_turbo/requests/{request_id}/response
text string, required stream bool, optional output_format string, optional voice_setting object, optional audio_setting object, optional language_boost string, optional pronunciation_dict object, optional voice_modify object, optional subtitle_enable bool, optional stream_options object, optional aigc_watermark bool, optional 
{
  "text": "你好，欢迎使用 SeaCloud 多模态模型 API。",
  "stream": false,
  "output_format": "url",
  "voice_setting": {
    "voice_id": "female-shaonv",
    "speed": 1.08,
    "vol": 1,
    "pitch": 0
  },
  "audio_setting": {
    "sample_rate": 32000,
    "bitrate": 128000,
    "channel": 1,
    "format": "mp3"
  },
  "language_boost": "Chinese",
  "aigc_watermark": false
}
 {request_id, outputs:[{type:"audio", url, content_type, file_name, file_size, duration, metadata?}], metadata}
minimax_speech_01_hd
Audio 
POST /v1/queue/minimax_speech_01_hd
GET  /v1/queue/minimax_speech_01_hd/requests/{request_id}/status
GET  /v1/queue/minimax_speech_01_hd/requests/{request_id}/response
text string, required stream bool, optional output_format string, optional voice_setting object, optional audio_setting object, optional language_boost string, optional pronunciation_dict object, optional voice_modify object, optional subtitle_enable bool, optional stream_options object, optional aigc_watermark bool, optional 
{
  "text": "你好，欢迎使用 SeaCloud 多模态模型 API。",
  "stream": false,
  "output_format": "url",
  "voice_setting": {
    "voice_id": "female-shaonv",
    "speed": 1.08,
    "vol": 1,
    "pitch": 0
  },
  "audio_setting": {
    "sample_rate": 32000,
    "bitrate": 128000,
    "channel": 1,
    "format": "mp3"
  },
  "language_boost": "Chinese",
  "aigc_watermark": false
}
 {request_id, outputs:[{type:"audio", url, content_type, file_name, file_size, duration, metadata?}], metadata}
minimax_speech_01_turbo
Audio 
POST /v1/queue/minimax_speech_01_turbo
GET  /v1/queue/minimax_speech_01_turbo/requests/{request_id}/status
GET  /v1/queue/minimax_speech_01_turbo/requests/{request_id}/response
text string, required stream bool, optional output_format string, optional voice_setting object, optional audio_setting object, optional language_boost string, optional pronunciation_dict object, optional voice_modify object, optional subtitle_enable bool, optional stream_options object, optional aigc_watermark bool, optional 
{
  "text": "你好，欢迎使用 SeaCloud 多模态模型 API。",
  "stream": false,
  "output_format": "url",
  "voice_setting": {
    "voice_id": "female-shaonv",
    "speed": 1.08,
    "vol": 1,
    "pitch": 0
  },
  "audio_setting": {
    "sample_rate": 32000,
    "bitrate": 128000,
    "channel": 1,
    "format": "mp3"
  },
  "language_boost": "Chinese",
  "aigc_watermark": false
}
 {request_id, outputs:[{type:"audio", url, content_type, file_name, file_size, duration, metadata?}], metadata}
mureka_lyrics_generator
Audio 
POST /v1/queue/mureka_lyrics_generator
GET  /v1/queue/mureka_lyrics_generator/requests/{request_id}/status
GET  /v1/queue/mureka_lyrics_generator/requests/{request_id}/response
prompt string, required 
{
  "prompt": "写一首关于夏夜海边和朋友重逢的中文流行歌词"
}
 {request_id, outputs:[{type:"text", text}], metadata}
mureka_song_generator
Audio 
POST /v1/queue/mureka_song_generator
GET  /v1/queue/mureka_song_generator/requests/{request_id}/status
GET  /v1/queue/mureka_song_generator/requests/{request_id}/response
lyrics string, required n int, optional prompt string, optional reference_id string, optional vocal_id string, optional melody_id string, optional stream bool, optional 
{
  "lyrics": "[Verse]\n晚风吹过海岸线\n我们把故事唱一遍",
  "prompt": "warm pop ballad, clean vocal, emotional chorus",
  "n": 1
}
 {request_id, outputs:[{type:"audio", url, content_type, file_name, file_size, duration, metadata?}], metadata}
tencent_hunyuan_3d
3D 
POST /v1/queue/tencent_hunyuan_3d
GET  /v1/queue/tencent_hunyuan_3d/requests/{request_id}/status
GET  /v1/queue/tencent_hunyuan_3d/requests/{request_id}/response
prompt string, optional image_base64 string, optional image_url string, optional result_format string, optional enable_pbr bool, optional multi_view_images array, optional 
{
  "prompt": "a small stylized robot, game-ready 3D asset"
}
 {request_id, outputs:[{type:"model3d", url, content_type, file_name, file_size, metadata?}], metadata}
tencent_hunyuan_3d_pro
3D 
POST /v1/queue/tencent_hunyuan_3d_pro
GET  /v1/queue/tencent_hunyuan_3d_pro/requests/{request_id}/status
GET  /v1/queue/tencent_hunyuan_3d_pro/requests/{request_id}/response
prompt string, optional image_base64 string, optional image_url string, optional face_count int, optional generate_type string, optional polygon_type string, optional enable_pbr bool, optional multi_view_images array, optional 
{
  "prompt": "a small stylized robot, game-ready 3D asset"
}
 {request_id, outputs:[{type:"model3d", url, content_type, file_name, file_size, metadata?}], metadata}
tencent_hunyuan_3d_rapid
3D 
POST /v1/queue/tencent_hunyuan_3d_rapid
GET  /v1/queue/tencent_hunyuan_3d_rapid/requests/{request_id}/status
GET  /v1/queue/tencent_hunyuan_3d_rapid/requests/{request_id}/response
prompt string, optional image_base64 string, optional image_url string, optional result_format string, optional enable_pbr bool, optional multi_view_images array, optional 
{
  "prompt": "a small stylized robot, game-ready 3D asset"
}
 {request_id, outputs:[{type:"model3d", url, content_type, file_name, file_size, metadata?}], metadata}