For Developers

API Documentation

Use the JuheNext API through OpenAI-, Anthropic-, or Gemini-compatible formats. This reference covers authentication, parameters, request examples, and response structures for every supported endpoint group.

Quick Start

Connect to the JuheNext API

Base URL

Use this host for every endpoint in this reference.

https://api.juhenextvip.com

Authentication

Send your JuheNext API Key as a Bearer token. Some Gemini-compatible clients may use x-goog-api-key instead.

Authorization: Bearer <YOUR_API_KEY>

Keep production Keys in server-side environment variables. Never expose them in browser code or a public repository.

Chat & Responses

OpenAI, Responses, Anthropic Messages, and Gemini-compatible interfaces.

POST/v1/chat/completions

Create Chat Completion

Creates a model response from a conversation. Streaming and tool calling are supported by compatible models.

Parameters

Name	Type	Location	Description
`model`Required	`string`	body	Exact model ID from the Models page.
`messages`Required	`array`	body	Conversation messages in chronological order.
`max_completion_tokens`Optional	`integer`	body	Maximum number of generated tokens.
`reasoning_effort`Optional	`string`	body	Reasoning effort for supported reasoning models. `noneminimallowmediumhighxhighmax`
`temperature`Optional	`number`	body	Sampling temperature. Support varies by model.
`stream`Optional	`boolean`	body	Returns Server-Sent Events when true.
`tools`Optional	`array`	body	Tools or functions available to the model.

cURL Request

application/json

curl --request POST \
  --url 'https://api.juhenextvip.com/v1/chat/completions' \
  --header 'Authorization: Bearer <YOUR_API_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "gpt-5.6-luna",
  "messages": [
    {
      "role": "developer",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'

Response Example

JSON

{
  "id": "chatcmpl_...",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 9,
    "total_tokens": 33
  }
}

Notes

For streaming, set stream to true and read events until [DONE].

POST/v1/responses

Create Response

Creates a response using the OpenAI Responses format, including instructions, reasoning, and tools.

Parameters

Name	Type	Location	Description
`model`Required	`string`	body	Exact model ID.
`input`Required	`string \| array`	body	Text or structured input items.
`instructions`Optional	`string`	body	System-level instructions for the response.
`max_output_tokens`Optional	`integer`	body	Maximum number of output tokens.
`reasoning`Optional	`object`	body	Reasoning configuration for supported models.
`stream`Optional	`boolean`	body	Streams response events when true.
`tools`Optional	`array`	body	Tools available during the response.

cURL Request

application/json

curl --request POST \
  --url 'https://api.juhenextvip.com/v1/responses' \
  --header 'Authorization: Bearer <YOUR_API_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "gpt-5.6-luna",
  "instructions": "Answer clearly and briefly.",
  "input": "Explain what an API gateway does."
}'

Response Example

JSON

{
  "id": "resp_...",
  "object": "response",
  "status": "completed",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "An API gateway is a single entry point..."
        }
      ]
    }
  ]
}

POST/v1/messages

Create Message

Creates a message using the Anthropic-compatible Messages format.

Parameters

Name	Type	Location	Description
`model`Required	`string`	body	Exact compatible model ID.
`messages`Required	`array`	body	Input messages for the conversation.
`max_tokens`Required	`integer`	body	Maximum number of generated tokens.
`stream`Optional	`boolean`	body	Streams message events when true.
`thinking`Optional	`object`	body	Extended-thinking configuration for supported models.

cURL Request

application/json

curl --request POST \
  --url 'https://api.juhenextvip.com/v1/messages' \
  --header 'Authorization: Bearer <YOUR_API_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "claude-sonnet-5",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Summarize the benefits of caching."
    }
  ]
}'

Response Example

JSON

{
  "id": "msg_...",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Caching reduces latency and upstream load..."
    }
  ],
  "stop_reason": "end_turn"
}

Notes

Use a model that supports the Messages format. Check the live Models page before integration.

POST/v1beta/models/{model}:{GenerateContentType}

Generate Gemini Content

Creates standard or streaming content using the Gemini-compatible interface.

Parameters

Name	Type	Location	Description
`model`Required	`string`	path	Gemini-compatible model ID.
`GenerateContentType`Required	`string`	path	Generation method appended after the model name. `generateContentstreamGenerateContent`
`contents`Required	`array`	body	Conversation content and parts.
`generationConfig`Optional	`object`	body	Optional sampling and output configuration.

cURL Request

application/json

curl --request POST \
  --url 'https://api.juhenextvip.com/v1beta/models/gemini-3.5-flash:generateContent' \
  --header 'Authorization: Bearer <YOUR_API_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
  "contents": [
    {
      "role": "user",
      "parts": [
        { "text": "Explain edge computing in one paragraph." }
      ]
    }
  ]
}'

Response Example

JSON

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          { "text": "Edge computing processes data closer..." }
        ]
      },
      "finishReason": "STOP"
    }
  ]
}

Images

Generate and edit images with OpenAI- and Gemini-compatible formats.

POST/v1/images/generations

Generate Image

Generates one or more images from a text prompt.

Parameters

Name	Type	Location	Description
`model`Required	`string`	body	Image-generation model ID.
`prompt`Required	`string`	body	Description of the image to generate.
`size`Optional	`string`	body	Preset size or custom WxH size supported by the model.
`n`Optional	`integer`	body	Number of images to generate when supported.
`response_format`Optional	`string`	body	Image return format when supported. `urlb64_json`

cURL Request

application/json

curl --request POST \
  --url 'https://api.juhenextvip.com/v1/images/generations' \
  --header 'Authorization: Bearer <YOUR_API_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "gpt-image-2-c",
  "prompt": "A flying white rabbit in a futuristic sci-fi style",
  "size": "1024x1536"
}'

Response Example

JSON

{
  "created": 1785859200,
  "data": [
    {
      "url": "https://example.com/generated-image.png"
    }
  ]
}

Notes

For compatible custom sizes, both dimensions must be multiples of 16, the longest edge must not exceed 3840, and the aspect ratio must not exceed 3:1.
Model-specific parameters and limits may differ. The Models page is the live source of availability.

POST/v1/images/edits

Edit Image

Edits an uploaded image according to a text prompt.

Parameters

Name	Type	Location	Description
`model`Required	`string`	body	Image-edit model ID.
`prompt`Required	`string`	body	Instructions describing the desired edit.
`image`Required	`file`	body	Source image file.
`size`Optional	`string`	body	Requested output size when supported.

cURL Request

multipart/form-data

curl --request POST \
  --url 'https://api.juhenextvip.com/v1/images/edits' \
  --header 'Authorization: Bearer <YOUR_API_KEY>' \
  --form 'model=gpt-image-2-c' \
  --form 'prompt=Transform the image into a Studio Ghibli-inspired style' \
  --form 'image=@/path/to/image.png' \
  --form 'size=1024x1536'

Response Example

JSON

{
  "created": 1785859200,
  "data": [
    {
      "url": "https://example.com/edited-image.png"
    }
  ]
}

POST/v1beta/models/{model}:{GenerateContentType}

Generate Nano Banana Image

Generates image content using the Gemini-compatible multimodal format.

Parameters

Name	Type	Location	Description
`model`Required	`string`	path	Compatible image model ID.
`contents`Required	`array`	body	Prompt and optional multimodal input parts.
`generationConfig`Optional	`object`	body	Output and generation options.

cURL Request

application/json

curl --request POST \
  --url 'https://api.juhenextvip.com/v1beta/models/gemini-3.1-flash-image:generateContent' \
  --header 'x-goog-api-key: <YOUR_API_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
  "contents": [
    {
      "parts": [
        { "text": "Create a minimal product photo of a glass teapot." }
      ]
    }
  ]
}'

Response Example

JSON

{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "inlineData": {
              "mimeType": "image/png",
              "data": "<BASE64_IMAGE_DATA>"
            }
          }
        ]
      }
    }
  ]
}

Notes

The generated image is returned in candidates[].content.parts[].inlineData.

POST/v1/images/generations

Generate Grok Image

Generates Grok images with aspect-ratio, resolution, and response-format controls.

Parameters

Name	Type	Location	Description
`model`Required	`string`	body	Grok image model ID.
`prompt`Required	`string`	body	Image prompt.
`aspect_ratio`Optional	`string`	body	Requested aspect ratio.
`n`Optional	`integer`	body	Number of images.
`resolution`Optional	`string`	body	Output resolution. `1k2k`
`response_format`Optional	`string`	body	Image return format. `urlb64_json`

cURL Request

application/json

curl --request POST \
  --url 'https://api.juhenextvip.com/v1/images/generations' \
  --header 'Authorization: Bearer <YOUR_API_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "grok-imagine-image",
  "prompt": "A quiet futuristic train station at blue hour",
  "aspect_ratio": "16:9",
  "resolution": "2k",
  "response_format": "url"
}'

Response Example

JSON

{
  "created": 1785859200,
  "data": [
    { "url": "https://example.com/grok-image.png" }
  ]
}

POST/v1/images/edits

Edit Grok Image

Edits one or more source images with a Grok-compatible image model.

Parameters

Name	Type	Location	Description
`model`Required	`string`	body	Grok image-edit model ID.
`prompt`Required	`string`	body	Editing instructions.
`image / images`Required	`file \| array`	body	One source image or multiple source images.
`response_format`Optional	`string`	body	Image return format. `urlb64_json`

cURL Request

application/json

curl --request POST \
  --url 'https://api.juhenextvip.com/v1/images/edits' \
  --header 'Authorization: Bearer <YOUR_API_KEY>' \
  --form 'model=grok-imagine-image' \
  --form 'prompt=Replace the background with a clean studio setting' \
  --form 'image=@/path/to/source.png'

Response Example

JSON

{
  "created": 1785859200,
  "data": [
    { "url": "https://example.com/grok-edited-image.png" }
  ]
}

Videos

Create asynchronous video tasks and retrieve their status and result.

POST/v1/videos

Create Grok Video

Creates an asynchronous Grok video-generation task.

Parameters

Name	Type	Location	Description
`model`Required	`string`	body	Video-generation model ID.
`prompt`Required	`string`	body	Description of the requested video.
`duration`Optional	`integer`	body	Requested duration in seconds.
`aspect_ratio`Optional	`string`	body	Requested aspect ratio.
`resolution`Optional	`string`	body	Output resolution. `480p720p1080p`

cURL Request

application/json

curl --request POST \
  --url 'https://api.juhenextvip.com/v1/videos' \
  --header 'Authorization: Bearer <YOUR_API_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "grok-imagine-video",
  "prompt": "A serene lake at sunrise with mist rolling over the water",
  "duration": 8,
  "aspect_ratio": "16:9",
  "resolution": "720p"
}'

Response Example

JSON

{
  "id": "task_...",
  "object": "video",
  "status": "queued"
}

GET/v1/videos/{task_id}

Retrieve Grok Video

Retrieves the current status and result of a video task.

Parameters

Name	Type	Location	Description
`task_id`Required	`string`	path	Public task ID returned by the create request.

cURL Request

application/json

curl --request GET \
  --url 'https://api.juhenextvip.com/v1/videos/task_...' \
  --header 'Authorization: Bearer <YOUR_API_KEY>'

Response Example

JSON

{
  "id": "task_...",
  "object": "video",
  "status": "completed",
  "url": "https://example.com/generated-video.mp4"
}

Notes

Poll at a reasonable interval and stop when the task reaches a terminal state.

Seedance 2.0

Review reusable media assets and create Seedance 2.0 video tasks.

POST/v1/video/generations

Submit Material Review

Submits one image, audio, or video URL for reusable-asset review.

Parameters

Name Type Location Description

Name	Type	Location	Description
`model`Required	`string`	body	Review model matching the media type. `seedance-review-imageseedance-review-audioseedance-review-video`
`prompt`Required	`string`	body	Short description of the asset.
`metadata.content`Required	`array`	body	Exactly one media item using image_url, audio_url, or video_url.

modelRequired

string

body

Review model matching the media type.

seedance-review-imageseedance-review-audioseedance-review-video

promptRequired

string

body

Short description of the asset.

metadata.contentRequired

array

body

Exactly one media item using image_url, audio_url, or video_url.

cURL Request

application/json

curl --request POST \
  --url 'https://api.juhenextvip.com/v1/video/generations' \
  --header 'Authorization: Bearer <YOUR_API_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "seedance-review-image",
  "prompt": "Review this character reference image",
  "metadata": {
    "content": [
      {
        "type": "image_url",
        "image_url": {
          "url": "https://example.com/reference.png"
        }
      }
    ]
  }
}'

Response Example

JSON

{
  "id": "task_...",
  "status": "queued",
  "model": "seedance-review-image"
}

Notes

The media URL must be an absolute HTTPS URL, and metadata.content must contain exactly one item.
After approval, save the persistent asset://asset-... identifier instead of a temporary signed URL.

GET/v1/video/generations/{task_id}

Retrieve Material Review

Retrieves a material-review result and its reusable asset identifier.

Parameters

Name	Type	Location	Description
`task_id`Required	`string`	path	Public review task ID.

cURL Request

application/json

curl --request GET \
  --url 'https://api.juhenextvip.com/v1/video/generations/task_...' \
  --header 'Authorization: Bearer <YOUR_API_KEY>'

Response Example

JSON

{
  "id": "task_...",
  "status": "completed",
  "asset": "asset://asset-..."
}

POST/v1/video/generations

Create Seedance Video

Creates a Seedance 2.0 asynchronous video-generation task.

Parameters

Name	Type	Location	Description
`model`Required	`string`	body	Seedance video model ID. `seedance-2-0seedance-2-0-fastseedance-2-0-mini`
`prompt`Required	`string`	body	Video prompt.
`seconds`Required	`string`	body	Duration as a JSON string from 4 to 15.
`images`Optional	`array`	body	Optional image references.
`metadata.resolution`Optional	`string`	body	Output resolution; fast and mini support 480p and 720p. `480p720p1080p`
`metadata.ratio`Optional	`string`	body	Output aspect ratio. `1:116:99:164:33:43:22:3`
`metadata.content`Optional	`array`	body	Reviewed asset references used by the task.
`metadata.callback_url`Optional	`string`	body	HTTPS callback URL for status updates.
`metadata.generate_audio`Optional	`boolean`	body	Whether to generate audio when supported.
`metadata.service_tier`Optional	`string`	body	Task service tier. `defaultflex`
`metadata.return_last_frame`Optional	`boolean`	body	Returns the last frame when supported.
`metadata.seed`Optional	`integer`	body	Generation seed; use -1 for a random seed.
`metadata.watermark`Optional	`boolean`	body	Whether to add a watermark.

cURL Request

application/json

curl --request POST \
  --url 'https://api.juhenextvip.com/v1/video/generations' \
  --header 'Authorization: Bearer <YOUR_API_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "seedance-2-0",
  "prompt": "Morning clouds drift slowly across snow-covered mountains as the camera moves forward smoothly",
  "seconds": "5",
  "metadata": {
    "resolution": "720p",
    "ratio": "16:9",
    "generate_audio": true,
    "seed": -1,
    "watermark": false
  }
}'

Response Example

JSON

{
  "id": "task_...",
  "status": "queued",
  "model": "seedance-2-0"
}

Notes

Additional metadata fields may be model-specific. Start with the minimum required fields and add controls only when needed.

GET/v1/video/generations/{task_id}

Retrieve Seedance Video

Retrieves a Seedance task status and the generated video result.

Parameters

Name	Type	Location	Description
`task_id`Required	`string`	path	Public task_... ID returned by JuheNext.

cURL Request

application/json

curl --request GET \
  --url 'https://api.juhenextvip.com/v1/video/generations/task_...' \
  --header 'Authorization: Bearer <YOUR_API_KEY>'

Response Example

JSON

{
  "id": "task_...",
  "status": "completed",
  "video_url": "https://example.com/seedance-video.mp4"
}

Notes

Always query with the public task_... ID returned by JuheNext, not an upstream internal ID.

Models & Usage

Create embeddings, list available models, and inspect API Key allowance.

POST/v1/embeddings

Create Embedding

Creates a vector representation of text input.

Parameters

Name	Type	Location	Description
`model`Required	`string`	body	Embedding model ID.
`input`Required	`string \| array`	body	Text or array of text to embed.
`encoding_format`Optional	`string`	body	Vector encoding format. `floatbase64`
`dimensions`Optional	`integer`	body	Requested vector dimensions when supported.

cURL Request

application/json

curl --request POST \
  --url 'https://api.juhenextvip.com/v1/embeddings' \
  --header 'Authorization: Bearer <YOUR_API_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "text-embedding-3-small",
  "input": "JuheNext makes model APIs easier to use.",
  "encoding_format": "float"
}'

Response Example

JSON

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0123, -0.0456, 0.0789]
    }
  ],
  "model": "text-embedding-3-small"
}

GET/v1/models

List Models

Lists model IDs currently available to the supplied API Key.

cURL Request

application/json

curl --request GET \
  --url 'https://api.juhenextvip.com/v1/models' \
  --header 'Authorization: Bearer <YOUR_API_KEY>'

Response Example

JSON

{
  "object": "list",
  "data": [
    {
      "id": "gpt-5.6-luna",
      "object": "model",
      "owned_by": "provider"
    }
  ]
}

Notes

Availability may vary by API Key and can change. Use this endpoint or the Models page as the live reference.

GET/api/usage/token

Retrieve Key Usage

Retrieves allowance and usage totals for the supplied API Key.

cURL Request

application/json

curl --request GET \
  --url 'https://api.juhenextvip.com/api/usage/token' \
  --header 'Authorization: Bearer <YOUR_API_KEY>'

Response Example

JSON

{
  "data": {
    "name": "JuheNext Key",
    "expires_at": -1,
    "total_granted": 5000000,
    "total_used": 1250000,
    "total_available": 3750000,
    "unlimited_quota": false
  }
}

Notes

The public Usage page can also display balance and up to 1,000 recent logs.
Field presence and numeric units follow the live API response.