Look up Rivya API model IDs, availability, supported modes, parameter tables, prompt limits, reference media rules, and model detail links.

This page is the model-level API reference for Rivya API v1.

The table below is generated from the same model catalog and public serializer used by /api/v1/models. It is not a hand-written fixed model count.

How To Read This Reference

Use the model id as model in POST /api/v1/generations for asynchronous image, video, and audio models.
Use chat model IDs in POST /api/v1/chat/completions.
Use top-level prompt for generation prompt text.
Use top-level message for Chat API turns.
Put asynchronous model-specific fields inside params.
Read api_input_status before building an integration. available_text and available_url_input can be tested without file upload; partial_requires_files means only some modes need Files API; requires_files_api means upload reference media through Files API before calling the model.
For chat models, read chat_capabilities for non-streaming support, SSE streaming support, image file_id attachments, web search, thoughts, and reasoning effort.
Model detail pages give product-level guidance and examples.

Use this reference with the debugger

Start from the quickstart, confirm model fields here, then run a mock or signed-in live request in the Developers debugger.

API Quickstart Online debugger

Z-Image

z-imageAvailable via APIText input ready

Image · Alibaba's lightweight text-to-image model. Fast single-image generation with 5 aspect ratios — ideal for quick concept drafts and social media visuals at just 1 credit.

API guide Model page

Base credits

Modes

text-to-image

API input

Text input ready

Inputs

text

Prompt limit

1000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "z-image",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "aspect_ratio": "1:1"
  }
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Parameters

key	Type	Required	Default	Range	Options
aspect_ratio	select	No	1:1	-	1:1, 4:3, 3:4, 16:9, 9:16

Nano Banana 2

nano-banana-2Available via APIPartial: Files API needed

Image · Google's next-gen image model with 4K resolution, 15 aspect ratios (including extreme 8:1), Google Search grounding, and up to 14 reference images — the most flexible image generator on Rivya.

API guide Model page

Base credits

Modes

text-to-image, image-to-image

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

20000 characters

Reference media

image · 14 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "nano-banana-2",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "aspect_ratio": "auto",
    "resolution": "1K",
    "output_format": "jpg",
    "google_search": "false"
  }
}

Reference rule

Reference image: Upload up to 14 image files for image projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
aspect_ratio	select	No	auto	-	auto, 1:1, 16:9, 9:16, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 21:9, 4:1, 1:4, 8:1, 1:8
resolution	select	No	1K	-	1K, 2K, 4K
output_format	select	No	jpg	-	jpg, png
google_search	select	No	false	-	false, true

Nano Banana Pro

nano-banana-proAvailable via APIPartial: Files API needed

Image · Google's premium image model with 4K output, 11 aspect ratios, and up to 8 reference images. Optimized for high-fidelity brand and campaign visuals with superior detail and color accuracy.

API guide Model page

Base credits

Modes

text-to-image, image-to-image

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

10000 characters

Reference media

image · 8 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "nano-banana-pro",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "aspect_ratio": "1:1",
    "resolution": "1K",
    "output_format": "png"
  }
}

Reference rule

Reference image: Upload up to 8 image files for image projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
aspect_ratio	select	No	1:1	-	1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, auto
resolution	select	No	1K	-	1K, 2K, 4K
output_format	select	No	png	-	png, jpg

Nano Banana

nano-bananaAvailable via APIPartial: Files API needed

Image · Google's flexible image model for text-to-image and image-to-image with 11 aspect ratios, up to 10 reference images, and PNG/JPEG output. A strong fit for portraits, product compositions, and wider landing-page visuals.

API guide Model page

Base credits

Modes

text-to-image, image-to-image

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

5000 characters

Reference media

image · 10 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "nano-banana",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "imageSize": "1:1",
    "output_format": "png"
  }
}

Reference rule

Reference image: Upload up to 10 image files for image projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
imageSize	select	No	1:1	-	1:1, 9:16, 16:9, 3:4, 4:3, 3:2, 2:3, 5:4, 4:5, 21:9, auto
output_format	select	No	png	-	png, jpeg

GPT Image 2

gpt-image-2Available via APIPartial: Files API needed

Image · OpenAI's newer GPT Image model on Rivya, with text-to-image, image-to-image, up to 16 reference images, and clear 1K / 2K / 4K credit tiers.

API guide Model page

Base credits

Modes

text-to-image, image-to-image

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

20000 characters

Reference media

image · 16 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "gpt-image-2",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "aspect_ratio": "1:1",
    "resolution": "1K"
  }
}

Reference rule

Reference images: Upload up to 16 image references for GPT Image 2 image-to-image tasks.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
aspect_ratio	select	No	1:1	-	auto, 1:1, 9:16, 16:9, 4:3, 3:4
resolution	select	No	1K	-	1K, 2K, 4K

GPT Image 1.5

gpt-image-1-5Available via APIPartial: Files API needed

Image · OpenAI's image model with medium/high quality tiers and up to 16 reference images. Excels at following complex instructions and rendering coherent scenes with accurate spatial relationships.

API guide Model page

Base credits

Modes

text-to-image, image-to-image

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

Reference media

image · 16 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "gpt-image-1-5",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "quality": "medium",
    "aspect_ratio": "1:1"
  }
}

Reference rule

Reference image: Upload up to 16 image files for image projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
quality	select	No	medium	-	medium, high
aspect_ratio	select	No	1:1	-	1:1, 2:3, 3:2

4o Image

4o-imageAvailable via APIText input ready

Image · OpenAI's 4o Image model is now available as a dedicated text-to-image path on Rivya. It keeps the page setup intentionally narrow for now: prompt plus 3 supported aspect ratios at a fixed 3 credits per image.

API guide Model page

Base credits

Modes

text-to-image

API input

Text input ready

Inputs

text

Prompt limit

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "4o-image",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "size": "1:1"
  }
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Parameters

key	Type	Required	Default	Range	Options
size	select	No	1:1	-	1:1, 3:2, 2:3

Seedream 5.0 Lite

seedream-5-liteAvailable via APIPartial: Files API needed

Image · ByteDance's lighter Seedream image model with shared pricing across text-to-image and image editing. It supports 8 aspect ratios, up to 14 reference images, and currently costs 6 credits per run.

API guide Model page

Base credits

Modes

text-to-image, image-to-image

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

3000 characters

Reference media

image · 14 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "seedream-5-lite",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "aspectRatio": "1:1",
    "quality": "basic"
  }
}

Reference rule

Reference image: Upload up to 14 image files for image projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
aspectRatio	select	No	1:1	-	1:1, 4:3, 3:4, 16:9, 9:16, 2:3, 3:2, 21:9
quality	select	No	basic	-	basic, high

Seedream 4.5

seedream-4-5Available via APIPartial: Files API needed

Image · ByteDance's high-end image model with 2K/4K quality tiers, 8 aspect ratios, and up to 14 reference images. Known for cinematic color grading and rich texture detail in fashion and lifestyle visuals.

API guide Model page

Base credits

Modes

text-to-image, image-to-image

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

3000 characters

Reference media

image · 14 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "seedream-4-5",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "aspectRatio": "1:1",
    "quality": "basic"
  }
}

Reference rule

Reference image: Upload up to 14 image files for image projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
aspectRatio	select	No	1:1	-	1:1, 4:3, 3:4, 16:9, 9:16, 2:3, 3:2, 21:9
quality	select	No	basic	-	basic, high

Seedream 4.0

seedream-4-0Available via APIPartial: Files API needed

Image · Seedream 4.0 is a balanced ByteDance image model on Rivya for text-to-image generation, reference-image editing, and explicit output controls.

API guide Model page

Base credits

Modes

text-to-image, image-to-image

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

5000 characters

Reference media

image · 10 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "seedream-4-0",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "image_size": "square_hd",
    "image_resolution": "1K",
    "max_images": 1,
    "seed": 0,
    "nsfw_checker": "false"
  }
}

Reference rule

Reference images: Upload up to 10 images for the Seedream 4.0 edit path.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
image_size	select	No	square_hd	-	square, square_hd, portrait_4_3, portrait_3_2, portrait_16_9, landscape_4_3, landscape_3_2, landscape_16_9, landscape_21_9
image_resolution	select	No	1K	-	1K, 2K, 4K
max_images	number	No	1	min 1 / max 6 / step 1	-
seed	number	No	-	min 0 / max 2147483647 / step 1	-
nsfw_checker	select	No	false	-	false, true

Seedream 3.0

seedream-3-0Available via APIText input ready

Image · Seedream 3.0 now returns as a standalone legacy image model on Rivya. It currently keeps only the public text-to-image path and costs 5 credits per run.

API guide Model page

Base credits

Modes

text-to-image

API input

Text input ready

Inputs

text

Prompt limit

5000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "seedream-3-0",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "image_size": "square_hd",
    "guidance_scale": 2.5,
    "seed": 0
  }
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Parameters

key	Type	Required	Default	Range	Options
image_size	select	No	square_hd	-	square, square_hd, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9
guidance_scale	number	No	2.5	min 1 / max 10 / step 0.1	-
seed	number	No	-	min 0 / max 2147483647	-

Grok Imagine

grok-imagineAvailable via APIPartial: Files API needed

Image · xAI's image model with strong creative interpretation and 5 aspect ratios. Single-image generation focused on artistic expression and unconventional visual styles.

API guide Model page

Base credits

Modes

text-to-image, image-to-image

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

5000 characters

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "grok-imagine",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "aspect_ratio": "1:1",
    "enable_pro": "false"
  }
}

Reference rule

Reference image: Upload up to 1 image file for image projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
aspect_ratio	select	No	1:1	-	1:1, 2:3, 3:2, 16:9, 9:16
enable_pro	select	No	false	-	false, true

Flux 2 Pro

flux-2-proAvailable via APIPartial: Files API needed

Image · Black Forest Labs' 32B-parameter flagship. Supports text-to-image and image-to-image with up to 8 reference images, 2K resolution, and accurate text rendering — built for product shots and brand visuals.

API guide Model page

Base credits

Modes

text-to-image, image-to-image

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

5000 characters

Reference media

image · 8 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "flux-2-pro",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "aspectRatio": "1:1",
    "resolution": "1K"
  }
}

Reference rule

Reference image: Upload up to 8 image files for image projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
aspectRatio	select	No	1:1	-	1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3
resolution	select	No	1K	-	1K, 2K

Flux 2 Flex

flux-2-flexAvailable via APIPartial: Files API needed

Image · Flux 2 family's editing-focused variant. Specializes in structural adjustments and style transfer with up to 8 reference images and 2K resolution — ideal for iterating on existing visuals.

API guide Model page

Base credits

Modes

text-to-image, image-to-image

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

5000 characters

Reference media

image · 8 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "flux-2-flex",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "aspectRatio": "1:1",
    "resolution": "1K"
  }
}

Reference rule

Reference image: Upload up to 8 image files for image projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
aspectRatio	select	No	1:1	-	1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3
resolution	select	No	1K	-	1K, 2K

Flux Kontext Max

flux-kontext-maxAvailable via APIPartial: Files API needed

Image · Black Forest Labs' enhanced Flux Kontext model for more demanding prompt-led generation and image editing tasks. Rivya currently keeps both text-to-image and image-to-image on the same async project and prices them at a fixed 8 credits per run under the platform's current policy.

API guide Model page

Base credits

Modes

text-to-image, image-to-image

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "flux-kontext-max",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "aspectRatio": "16:9",
    "outputFormat": "jpeg",
    "enableTranslation": "true",
    "promptUpsampling": "false",
    "safetyTolerance": 2,
    "watermark": "Optional watermark text"
  }
}

Reference rule

Reference image: Upload up to 1 image file for image editing projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
aspectRatio	select	No	16:9	-	21:9, 16:9, 4:3, 1:1, 3:4, 9:16
outputFormat	select	No	jpeg	-	jpeg, png
enableTranslation	select	No	true	-	true, false
promptUpsampling	select	No	false	-	false, true
safetyTolerance	number	No	2	min 0 / max 6	-
watermark	text	No	-	-	-

Flux Kontext Pro

flux-kontext-proAvailable via APIPartial: Files API needed

Image · Black Forest Labs' lower-cost Flux Kontext project for text-to-image and single-image editing. Rivya currently exposes both text-to-image and image-to-image on the same async image project, with fixed 4-credit pricing for both modes under the current platform pricing policy.

API guide Model page

Base credits

Modes

text-to-image, image-to-image

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "flux-kontext-pro",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "aspectRatio": "16:9",
    "outputFormat": "jpeg",
    "enableTranslation": "true",
    "promptUpsampling": "false",
    "safetyTolerance": 2,
    "watermark": "Optional watermark text"
  }
}

Reference rule

Reference image: Upload up to 1 image file for image editing projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
aspectRatio	select	No	16:9	-	21:9, 16:9, 4:3, 1:1, 3:4, 9:16
outputFormat	select	No	jpeg	-	jpeg, png
enableTranslation	select	No	true	-	true, false
promptUpsampling	select	No	false	-	false, true
safetyTolerance	number	No	2	min 0 / max 6	-
watermark	text	No	-	-	-

Qwen2 Image

qwen2-imageAvailable via APIPartial: Files API needed

Image · Alibaba's Qwen2 image model is currently integrated on Rivya as one fixed-price image project. It safely covers text-to-image and image-to-image with the shared aspect-ratio subset both public docs expose, plus PNG/JPEG output, seed reuse, and a simple NSFW switch.

API guide Model page

Base credits

Modes

text-to-image, image-to-image

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

800 characters

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "qwen2-image",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "image_size": "16:9",
    "output_format": "png",
    "seed": 0,
    "nsfw_checker": "false"
  }
}

Reference rule

Reference image: Upload up to 1 image file for image projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
image_size	select	No	16:9	-	1:1, 3:4, 4:3, 9:16, 16:9
output_format	select	No	png	-	png, jpeg
seed	number	No	-	min 0	-
nsfw_checker	select	No	false	-	false, true

Qwen Image

qwen-imageAvailable via APIPartial: Files API needed

Image · Alibaba Qwen family's image model with HD presets (Square, Portrait, Landscape) and PNG/JPEG output. Strong at Chinese-language prompts and culturally nuanced visual generation.

API guide Model page

Base credits

Modes

text-to-image, image-to-image

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

5000 characters

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "qwen-image",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "image_size": "square_hd",
    "output_format": "png"
  }
}

Reference rule

Reference image: Upload up to 1 image file for image projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
image_size	select	No	square_hd	-	square, square_hd, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9
output_format	select	No	png	-	png, jpeg

Midjourney

midjourneyAvailable via APIPartial: Files API needed

Image · Midjourney's V7 image model for text-to-image and image-to-image with Niji anime modes, 3 speed tiers (Relaxed/Fast/Turbo), style references, and Omni Reference-driven consistency. Still the benchmark for cinematic art, illustrations, and moodboards.

API guide Model page

Base credits

Modes

text-to-image, image-to-image

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

2000 characters

Reference media

image · 4 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "midjourney",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "speed": "relaxed",
    "aspectRatio": "1:1",
    "version": "7"
  }
}

Reference rule

Reference image: Upload up to 4 image files for image projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
speed	select	No	relaxed	-	relaxed, fast, turbo
aspectRatio	select	No	1:1	-	1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3
version	select	No	7	-	7, 6.1, 6, niji7, niji6

Recraft Remove Background

recraft-remove-backgroundAvailable via APIFiles API needed

Image · Recraft's background-removal model on Rivya for isolating the subject from one existing image. Use it when the next step needs a transparent asset, a clean cutout, or a source image without the original background.

API guide Model page

Base credits

Modes

image-to-image

API input

Files API needed

Inputs

file

Prompt limit

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

No runnable Public API example is shown for this model.

Reference rule

Source image: Upload exactly 1 image. Cleaner subject edges usually produce cleaner cutouts.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

File-based modes need /api/v1/files before they can be shown as complete API-ready examples. Files API

Parameters

No extra model parameter is required.

Recraft Crisp Upscale

recraft-crisp-upscaleAvailable via APIFiles API needed

Image · Recraft's light image-upscaling model on Rivya for low-cost sharpness and clarity boosts on one approved still. Use it when the chosen image only needs a cheap polish pass before export, not a heavier delivery-grade upscale.

API guide Model page

Base credits

Modes

image-to-image

API input

Files API needed

Inputs

file

Prompt limit

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

No runnable Public API example is shown for this model.

Reference rule

Source image: Upload exactly 1 image. This option is meant for a quick low-cost polish pass.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

File-based modes need /api/v1/files before they can be shown as complete API-ready examples. Files API

Parameters

No extra model parameter is required.

Wan 2.7 Image Pro

wan-2-7-image-proAvailable via APIPartial: Files API needed

Image · Alibaba's higher-end Wan 2.7 image model, currently exposed on Rivya as a separate image slot for text-to-image and image editing. Pricing stays fixed at 12 credits per run by explicitly keeping generation to a single output image.

API guide Model page

Base credits

Modes

text-to-image, image-to-image

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

5000 characters

Reference media

image · 9 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "wan-2-7-image-pro",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "aspect_ratio": "1:1",
    "resolution": "2K",
    "watermark": "false",
    "seed": 0
  }
}

Reference rule

Reference image: Upload up to 9 image files for image editing projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
aspect_ratio	select	No	1:1	-	1:1, 16:9, 4:3, 21:9, 3:4, 9:16, 8:1, 1:8
resolution	select	No	2K	-	1K, 2K
watermark	select	No	false	-	false, true
seed	number	No	-	min 0 / max 2147483647 / step 1	-

Wan 2.7 Image

wan-2-7-imageAvailable via APIPartial: Files API needed

Image · Alibaba's standard Wan 2.7 image model is exposed on Rivya as its own image slot for text-to-image and image editing, and currently costs 5 credits per run.

API guide Model page

Base credits

Modes

text-to-image, image-to-image

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

5000 characters

Reference media

image · 9 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "wan-2-7-image",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "aspect_ratio": "1:1",
    "resolution": "2K",
    "watermark": "false",
    "seed": 0
  }
}

Reference rule

Reference image: Upload up to 9 image files for image editing projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
aspect_ratio	select	No	1:1	-	1:1, 16:9, 4:3, 21:9, 3:4, 9:16, 8:1, 1:8
resolution	select	No	2K	-	1K, 2K
watermark	select	No	false	-	false, true
seed	number	No	-	min 0 / max 2147483647	-

Google Imagen4 Ultra

google-imagen4-ultraAvailable via APIText input ready

Image · Google Imagen4 Ultra is Rivya's premium Imagen text-to-image tier. It is currently integrated as a fixed 12-credit, single-image project with public prompt, negative prompt, aspect ratio, and seed controls.

API guide Model page

Base credits

Modes

text-to-image

API input

Text input ready

Inputs

text

Prompt limit

5000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "google-imagen4-ultra",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "aspect_ratio": "1:1",
    "negative_prompt": "Optional things to avoid",
    "seed": "Optional seed value"
  }
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Parameters

key	Type	Required	Default	Range	Options
aspect_ratio	select	No	1:1	-	1:1, 16:9, 9:16, 3:4, 4:3
negative_prompt	text	No	-	-	-
seed	text	No	-	-	-

Google Imagen4

google-imagen4Available via APIText input ready

Image · Google Imagen4 is Rivya's standard Imagen text-to-image tier. It is currently integrated as a fixed 8-credit, single-image project with public prompt, negative prompt, aspect ratio, and seed controls.

API guide Model page

Base credits

Modes

text-to-image

API input

Text input ready

Inputs

text

Prompt limit

5000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "google-imagen4",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "aspect_ratio": "1:1",
    "negative_prompt": "Optional things to avoid",
    "seed": "Optional seed value"
  }
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Parameters

key	Type	Required	Default	Range	Options
aspect_ratio	select	No	1:1	-	1:1, 16:9, 9:16, 3:4, 4:3
negative_prompt	text	No	-	-	-
seed	text	No	-	-	-

Google Imagen4 Fast

google-imagen4-fastAvailable via APIText input ready

Image · Google Imagen4 Fast is Rivya's lightweight Imagen text-to-image tier. It currently keeps a single-image project, uses fixed 4-credit pricing, and exposes the public prompt, negative prompt, aspect ratio, and seed controls without opening multi-image output.

API guide Model page

Base credits

Modes

text-to-image

API input

Text input ready

Inputs

text

Prompt limit

5000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "google-imagen4-fast",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "aspect_ratio": "16:9",
    "negative_prompt": "Optional things to avoid",
    "seed": 0
  }
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Parameters

key	Type	Required	Default	Range	Options
aspect_ratio	select	No	16:9	-	1:1, 16:9, 9:16, 3:4, 4:3
negative_prompt	text	No	-	-	-
seed	number	No	-	min 0	-

Topaz Image Upscaler

topaz-image-upscaleAvailable via APIFiles API needed

Image · Topaz's delivery-grade image upscaler on Rivya for approved stills that need a real size jump. Use it when the composition is already final and the remaining problem is export resolution, review size, or print readiness.

API guide Model page

Base credits

Modes

image-to-image

API input

Files API needed

Inputs

file

Prompt limit

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

No runnable Public API example is shown for this model.

Reference rule

Source image: Upload 1 approved image you want to preserve. This option is for enlargement, not creative re-editing.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

File-based modes need /api/v1/files before they can be shown as complete API-ready examples. Files API

Parameters

key	Type	Required	Default	Range	Options
upscale_factor	select	No	1	-	1, 2, 4, 8

Ideogram V3

ideogram-v3Available via APIText input ready

Image · Ideogram V3 is Rivya's text-to-image model for text rendering, poster layouts, and design-first image prompts. Current pricing is 4 credits for TURBO, 7 for BALANCED, and 10 for QUALITY.

API guide Model page

Base credits

Modes

text-to-image

API input

Text input ready

Inputs

text

Prompt limit

5000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "ideogram-v3",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "rendering_speed": "BALANCED",
    "style": "AUTO",
    "expand_prompt": "true",
    "image_size": "square_hd",
    "seed": 0,
    "negative_prompt": "Optional things to avoid"
  }
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Parameters

key	Type	Required	Default	Range	Options
rendering_speed	select	No	BALANCED	-	TURBO, BALANCED, QUALITY
style	select	No	AUTO	-	AUTO, GENERAL, REALISTIC, DESIGN
expand_prompt	select	No	true	-	true, false
image_size	select	No	square_hd	-	square, square_hd, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9
seed	number	No	-	min 0	-
negative_prompt	text	No	-	-	-

Ideogram V3 Reframe

ideogram-v3-reframeAvailable via APIFiles API needed

Image · Ideogram V3 Reframe is currently integrated on Rivya as a single-image reframing project with rendering-speed pricing. Current pricing is 4 credits for TURBO, 7 for BALANCED, and 10 for QUALITY.

API guide Model page

Base credits

Modes

image-to-image

API input

Files API needed

Inputs

file

Prompt limit

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

No runnable Public API example is shown for this model.

Reference rule

Reference image: Upload exactly 1 image file for this project.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

File-based modes need /api/v1/files before they can be shown as complete API-ready examples. Files API

Parameters

key	Type	Required	Default	Range	Options
rendering_speed	select	No	BALANCED	-	TURBO, BALANCED, QUALITY
style	select	No	AUTO	-	AUTO, GENERAL, REALISTIC, DESIGN
image_size	select	No	square_hd	-	square, square_hd, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9
seed	number	No	-	min 0	-

Ideogram V3 Remix

ideogram-v3-remixAvailable via APIFiles API needed

Image · Ideogram V3 Remix is currently integrated on Rivya as a single-image remix project with rendering-speed pricing. Current pricing is 4 credits for TURBO, 7 for BALANCED, and 10 for QUALITY.

API guide Model page

Base credits

Modes

image-to-image

API input

Files API needed

Inputs

file

Prompt limit

5000 characters

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

No runnable Public API example is shown for this model.

Reference rule

Reference image: Upload exactly 1 image file for this project.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

File-based modes need /api/v1/files before they can be shown as complete API-ready examples. Files API

Parameters

key	Type	Required	Default	Range	Options
rendering_speed	select	No	BALANCED	-	TURBO, BALANCED, QUALITY
style	select	No	AUTO	-	AUTO, GENERAL, REALISTIC, DESIGN
expand_prompt	select	No	true	-	true, false
image_size	select	No	square_hd	-	square, square_hd, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9
seed	number	No	-	min 0	-
strength	number	No	0.8	min 0.01 / max 1	-
negative_prompt	text	No	-	-	-

Ideogram Character

ideogram-characterAvailable via APIFiles API needed

Image · Character-consistency option for turning one approved character image into new scenes, outfits, and formats. Use it when identity retention matters more than broad image editing and you only need one output image at a time.

API guide Model page

Base credits

Modes

image-to-image

API input

Files API needed

Inputs

file

Prompt limit

5000 characters

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

No runnable Public API example is shown for this model.

Reference rule

Character reference image: Upload 1 clear character reference image. This option ignores extra images and keeps output to a single result.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

File-based modes need /api/v1/files before they can be shown as complete API-ready examples. Files API

Parameters

key	Type	Required	Default	Range	Options
rendering_speed	select	No	BALANCED	-	TURBO, BALANCED, QUALITY
style	select	No	AUTO	-	AUTO, REALISTIC, FICTION
expand_prompt	select	No	true	-	true, false
image_size	select	No	square_hd	-	square, square_hd, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9
seed	number	No	-	min 0	-
negative_prompt	text	No	-	-	-

Seedance 2.0

seedance-2Available via APIText input ready

Video · ByteDance's full Seedance 2.0 video model with explicit support for prompt-only generation, frame-driven animation, and multimodal reference generation. Rivya keeps the documented role split explicit so frame inputs and multimodal references stay mutually exclusive instead of collapsing into one ambiguous upload bucket.

API guide Model page

Base credits

175

Modes

text-to-video, image-to-video, reference-to-video

API input

Text input ready

Inputs

text

Prompt limit

2500 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "seedance-2",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "seedance_scene": "text",
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "duration": 5,
    "generate_audio": "true",
    "return_last_frame": "false",
    "web_search": "false",
    "nsfw_checker": "false"
  }
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Parameters

key	Type	Required	Default	Range	Options
seedance_scene	select	No	text	-	text, frames, reference
resolution	select	No	720p	-	480p, 720p
aspect_ratio	select	No	16:9	-	1:1, 4:3, 3:4, 16:9, 9:16, 21:9, adaptive
duration	number	No	5	min 4 / max 15	-
generate_audio	select	No	true	-	true, false
return_last_frame	select	No	false	-	false, true
web_search	select	No	false	-	false, true
nsfw_checker	select	No	false	-	false, true

Seedance 2.0 Fast

seedance-2-fastAvailable via APIText input ready

Video · ByteDance's faster Seedance 2.0 video model with full scene routing for prompt-only generation, frame-driven image animation, and multimodal reference video generation. Rivya keeps the documented scene split explicit so first/last-frame inputs do not collide with reference image, video, and audio roles.

API guide Model page

Base credits

140

Modes

text-to-video, image-to-video, reference-to-video

API input

Text input ready

Inputs

text

Prompt limit

2500 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "seedance-2-fast",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "seedance_scene": "text",
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "duration": 5,
    "generate_audio": "true",
    "return_last_frame": "false",
    "web_search": "false",
    "nsfw_checker": "false"
  }
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Parameters

key	Type	Required	Default	Range	Options
seedance_scene	select	No	text	-	text, frames, reference
resolution	select	No	720p	-	480p, 720p
aspect_ratio	select	No	16:9	-	1:1, 4:3, 3:4, 16:9, 9:16, 21:9, adaptive
duration	number	No	5	min 4 / max 15	-
generate_audio	select	No	true	-	true, false
return_last_frame	select	No	false	-	false, true
web_search	select	No	false	-	false, true
nsfw_checker	select	No	false	-	false, true

Seedance 1.5 Pro

seedance-1-5-proAvailable via APIPartial: Files API needed

Video · ByteDance's flagship video model for text-to-video and image-to-video with native audio-visual sync. 480p–1080p, 4–12s clips, 6 aspect ratios, dynamic/fixed lens control, optional audio generation, and lip-sync support.

API guide Model page

Base credits

Modes

text-to-video, image-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

2500 characters

Reference media

image · 2 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "seedance-1-5-pro",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "resolution": "720p",
    "duration": "8",
    "generate_audio": "false",
    "aspectRatio": "1:1",
    "fixed_lens": "false"
  }
}

Reference rule

Reference image: Upload up to 2 image files for image projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
resolution	select	No	720p	-	480p, 720p, 1080p
duration	select	No	8	-	4, 8, 12
generate_audio	select	No	false	-	false, true
aspectRatio	select	No	1:1	-	1:1, 4:3, 3:4, 16:9, 9:16, 21:9
fixed_lens	select	No	false	-	false, true

Seedance 1.0 Pro

seedance-1-0-proAvailable via APIPartial: Files API needed

Video · ByteDance's Seedance 1.0 Pro model, exposed on Rivya as the standard 1.0 Pro option for both text-to-video and image-to-video. It keeps the current page setup aligned to the public V1 Pro docs with resolution, duration, camera lock, seed, and safety-check controls.

API guide Model page

Base credits

Modes

text-to-video, image-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

10000 characters

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "seedance-1-0-pro",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "resolution": "720p",
    "duration": "5",
    "aspect_ratio": "16:9",
    "camera_fixed": "false",
    "seed": -1,
    "enable_safety_checker": "true"
  }
}

Reference rule

Reference image: Upload 1 image file for image-to-video runs.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
resolution	select	No	720p	-	480p, 720p, 1080p
duration	select	No	5	-	5, 10
aspect_ratio	select	No	16:9	-	21:9, 16:9, 4:3, 1:1, 3:4, 9:16
camera_fixed	select	No	false	-	false, true
seed	number	No	-1	min -1 / max 2147483647	-
enable_safety_checker	select	No	true	-	true, false

Seedance 1.0 Pro Fast

seedance-1-0-pro-fastAvailable via APIFiles API needed

Video · ByteDance's fast image-to-video model. Animates a single reference image into 5s or 10s clips at 720p/1080p — optimized for speed when you need quick video from a still.

API guide Model page

Base credits

Modes

image-to-video

API input

Files API needed

Inputs

file

Prompt limit

10000 characters

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

No runnable Public API example is shown for this model.

Reference rule

Reference image: Upload 1 source image to animate it into video.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

File-based modes need /api/v1/files before they can be shown as complete API-ready examples. Files API

Parameters

key	Type	Required	Default	Range	Options
resolution	select	No	720p	-	720p, 1080p
duration	select	No	5	-	5, 10

Seedance 1.0 Lite

seedance-1-0-liteAvailable via APIPartial: Files API needed

Video · ByteDance's Seedance 1.0 Lite model is exposed on Rivya as the lighter 1.0 option for both text-to-video and image-to-video. It follows the public V1 Lite parameter set and currently uses a lower pricing ladder than Seedance 1.0 Pro.

API guide Model page

Base credits

Modes

text-to-video, image-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

10000 characters

Reference media

image · 2 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "seedance-1-0-lite",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "resolution": "720p",
    "duration": "5",
    "aspect_ratio": "16:9",
    "camera_fixed": "false",
    "seed": -1,
    "enable_safety_checker": "true"
  }
}

Reference rule

Reference image: Upload 1 source image for image-to-video, or 2 images when you also want to provide an optional end frame.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
resolution	select	No	720p	-	480p, 720p, 1080p
duration	select	No	5	-	5, 10
aspect_ratio	select	No	16:9	-	16:9, 4:3, 1:1, 3:4, 9:16, 9:21
camera_fixed	select	No	false	-	false, true
seed	number	No	-1	min -1 / max 2147483647	-
enable_safety_checker	select	No	true	-	true, false

HappyHorse 1.0

happyhorse-1-0Available via APIPartial: Files API needed

Video · A flexible AI video model on Rivya for text-to-video, single-image motion, multi-image reference video, and video editing from one public model page.

API guide Model page

Base credits

Modes

text-to-video, image-to-video, reference-to-video, video-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

5000 characters

Reference media

image, video · 10 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "happyhorse-1-0",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "duration": 5,
    "audio_setting": "auto",
    "seed": 0
  }
}

Reference rule

Reference media: Use up to 9 images without a video, or 1 video with up to 5 image references for video editing.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
resolution	select	No	1080p	-	720p, 1080p
aspect_ratio	select	No	16:9	-	16:9, 9:16, 1:1, 4:3, 3:4
duration	number	No	5	min 3 / max 15	-
audio_setting	select	No	auto	-	auto, origin
seed	number	No	0	min 0 / max 2147483647	-

Wan 2.7 Video

wan-2-7-videoAvailable via APIPartial: Files API needed

Video · Alibaba's newer Wan video line with pricing by resolution and duration. Rivya currently exposes text-to-video, image-to-video, and video editing in one model slot, starting at 80 credits per generation.

API guide Model page

Base credits

Modes

text-to-video, image-to-video, video-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

5000 characters

Reference media

image, video · 2 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "wan-2-7-video",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "resolution": "720p",
    "duration": "5",
    "aspect_ratio": "16:9",
    "negative_prompt": "Optional exclusions or failure modes to avoid.",
    "prompt_extend": "true",
    "watermark": "false",
    "audio_setting": "auto",
    "seed": 0
  }
}

Reference rule

Reference media: Upload up to 2 assets. Use up to 2 images for image-to-video, or 1 video plus 1 optional image for video editing.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
resolution	select	No	720p	-	720p, 1080p
duration	select	No	5	-	5, 10, 15
aspect_ratio	select	No	16:9	-	16:9, 9:16, 1:1, 4:3, 3:4
negative_prompt	text	No	-	-	-
prompt_extend	select	No	true	-	true, false
watermark	select	No	false	-	false, true
audio_setting	select	No	auto	-	auto, origin
seed	number	No	-	min 0 / max 2147483647	-

Wan 2.6

wan-2-6Available via APIPartial: Files API needed

Video · Alibaba's triple-mode Wan option on Rivya: text-to-video, image-to-video, and source-video editing in one project. It supports 720p/1080p, 5–15 second clips, and one image or one source video at a time.

API guide Model page

Base credits

Modes

text-to-video, image-to-video, video-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

5000 characters

Reference media

image, video · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "wan-2-6",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "resolution": "720p",
    "duration": "5"
  }
}

Reference rule

Reference media: Upload up to 1 image / video file for image / video projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
resolution	select	No	720p	-	720p, 1080p
duration	select	No	5	-	5, 10, 15

Wan 2.5 Video

wan-2-5-videoAvailable via APIPartial: Files API needed

Video · Wan 2.5 is now exposed on Rivya as one shared entry for text-to-video and image-to-video. Current pricing is `720p_5 = 60`, `720p_10 = 120`, `1080p_5 = 100`, and `1080p_10 = 200` credits.

API guide Model page

Base credits

Modes

text-to-video, image-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

5000 characters

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "wan-2-5-video",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "resolution": "720p",
    "duration": "5",
    "aspect_ratio": "16:9",
    "enable_prompt_expansion": "false",
    "seed": 0,
    "negative_prompt": "Optional exclusions or failure modes to avoid.",
    "nsfw_checker": "false"
  }
}

Reference rule

Reference image: Upload up to 1 image file for image-to-video mode.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
resolution	select	No	720p	-	720p, 1080p
duration	select	No	5	-	5, 10
aspect_ratio	select	No	16:9	-	16:9, 9:16, 1:1
enable_prompt_expansion	select	No	false	-	false, true
seed	number	No	-	min 0 / max 2147483647	-
negative_prompt	text	No	-	-	-
nsfw_checker	select	No	false	-	false, true

Wan 2.2 A14B Turbo

wan-2-2-a14b-turboAvailable via APIPartial: Files API needed

Video · Wan 2.2 A14B Turbo now covers text-to-video, image-to-video, plus an image-and-audio-driven video path on Rivya. Current pricing is `480p = 8` and `720p = 12` for text or image runs, plus `480p = 16`, `580p = 20`, and `720p = 24` when one image and one audio clip drive the result.

API guide Model page

Base credits

Modes

text-to-video, image-to-video, speech-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

5000 characters

Reference media

image, audio · 2 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "wan-2-2-a14b-turbo",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "enable_prompt_expansion": "false",
    "seed": 0,
    "acceleration": "none",
    "num_frames": 80,
    "frames_per_second": 16,
    "negative_prompt": "Optional exclusions or failure modes to avoid.",
    "num_inference_steps": 27,
    "guidance_scale": 3.5,
    "shift": 5,
    "enable_safety_checker": "true"
  }
}

Reference rule

Reference media: Upload up to 2 assets. Text mode needs none, image-to-video uses 1 image, and the image-plus-audio-driven path uses 1 image plus 1 audio clip.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
resolution	select	No	720p	-	480p, 580p, 720p
aspect_ratio	select	No	16:9	-	16:9, 9:16
enable_prompt_expansion	select	No	false	-	false, true
seed	number	No	-	min 0 / max 2147483647	-
acceleration	select	No	none	-	none, regular
num_frames	number	No	80	min 40 / max 120 / step 1	-
frames_per_second	number	No	16	min 4 / max 60 / step 1	-
negative_prompt	text	No	-	-	-
num_inference_steps	number	No	27	min 2 / max 40 / step 1	-
guidance_scale	number	No	3.5	min 1 / max 10 / step 0.1	-
shift	number	No	5	min 1 / max 10 / step 0.1	-
enable_safety_checker	select	No	true	-	true, false

Wan Animate Replace

wan-2-2-animate-replaceAvailable via APIURL input ready

Video · Wan's character-replacement video model on Rivya for swapping who appears in an existing clip. Use one public source video URL, one public replacement image URL, and a resolution tier when the motion is already right and the visible subject needs to change.

API guide Model page

Base credits

Modes

video-to-video

API input

URL input ready

Inputs

url

Prompt limit

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "wan-2-2-animate-replace",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "video_url": "https://...",
    "image_url": "https://...",
    "resolution": "480p"
  }
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

This model accepts public URL input through model parameters.

Parameters

key	Type	Required	Default	Range	Options
video_url	text	No	-	-	-
image_url	text	No	-	-	-
resolution	select	No	480p	-	480p, 580p, 720p

Hailuo 2.3

hailuo-2-3Available via APIFiles API needed

Video · MiniMax's image-to-video model with Standard/Pro quality tiers, 768P/1080P resolution, and 6s or 10s clips. Known for smoother motion and natural transitions from still images.

API guide Model page

Base credits

Modes

image-to-video

API input

Files API needed

Inputs

file

Prompt limit

5000 characters

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

No runnable Public API example is shown for this model.

Reference rule

Reference image: Upload up to 1 image file for image projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

File-based modes need /api/v1/files before they can be shown as complete API-ready examples. Files API

Parameters

key	Type	Required	Default	Range	Options
quality	select	No	standard	-	standard, pro
resolution	select	No	768P	-	768P, 1080P
duration	select	No	6	-	6, 10

Hailuo Pro

hailuo-proAvailable via APIPartial: Files API needed

Video · MiniMax's older Hailuo Pro video model is connected here as one fixed Pro-tier model for both text-to-video and image-to-video. Image mode accepts 1 or 2 reference images, with the second image used as the last frame, and each run currently costs 57 credits.

API guide Model page

Base credits

Modes

text-to-video, image-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

1500 characters

Reference media

image · 2 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "hailuo-pro",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "prompt_optimizer": "false"
  }
}

Reference rule

Reference images: Image mode accepts up to 2 images, and the second image becomes the last frame.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
prompt_optimizer	select	No	false	-	false, true

Hailuo Standard

hailuo-standardAvailable via APIPartial: Files API needed

Video · MiniMax's older Hailuo Standard video model, unified here as one model for both text-to-video and image-to-video. Image mode accepts 1 or 2 reference images, with the second image used as the last frame, and the currently verified public pricing tiers range from 12 to 50 credits.

API guide Model page

Base credits

Modes

text-to-video, image-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

1500 characters

Reference media

image · 2 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "hailuo-standard",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "duration": "6",
    "resolution": "512P",
    "prompt_optimizer": "false"
  }
}

Reference rule

Reference images: Image mode accepts up to 2 images, and the second image becomes the last frame.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
duration	select	No	6	-	6, 10
resolution	select	No	512P	-	512P, 768P
prompt_optimizer	select	No	false	-	false, true

Kling 3.0

kling-3-0Available via APIPartial: Files API needed

Video · Kuaishou's premium video model for text-to-video and image-to-video, with Standard (720P) / Pro (1080P) tiers, single or multi-shot structure, 3–15s duration, optional audio generation, and up to 2 reference images.

API guide Model page

Base credits

Modes

text-to-video, image-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

2000 characters

Reference media

image · 2 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "kling-3-0",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "mode": "pro",
    "multi_shots": "false",
    "duration": "5",
    "sound": "false",
    "aspect_ratio": "16:9"
  }
}

Reference rule

Reference media: Upload up to 2 image files total for image-to-video projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
mode	select	No	pro	-	std, pro
multi_shots	select	No	false	-	false, true
duration	select	No	5	-	3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
sound	select	No	false	-	false, true
aspect_ratio	select	No	16:9	-	16:9, 9:16, 1:1

Kling 3.0 motion-control

kling-3-0-motion-controlAvailable via APIFiles API needed

Video · Newer Kling motion-control option for driving one subject from one reference image plus one motion video, with explicit background-source choice. Use it when you want motion transfer plus stronger control over whether the scene should come from the video or the image.

API guide Model page

Base credits

Modes

video-to-video

API input

Files API needed

Inputs

file

Prompt limit

2500 characters

Reference media

image, video · 2 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

No runnable Public API example is shown for this model.

Reference rule

Reference image + motion video: Upload exactly 1 character image and 1 motion clip. Use 3.0 when you need both orientation control and a background-source choice.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

File-based modes need /api/v1/files before they can be shown as complete API-ready examples. Files API

Parameters

key	Type	Required	Default	Range	Options
mode	select	No	pro	-	std, pro
character_orientation	select	No	video	-	video, image
background_source	select	No	input_video	-	input_video, input_image

Kling 2.6

kling-2-6Available via APIPartial: Files API needed

Video · Kuaishou's video model with optional audio generation, 5s/10s clips, and 3 aspect ratios. Strong at human motion and expressive character animation with natural physics.

API guide Model page

Base credits

Modes

text-to-video, image-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

1000 characters

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "kling-2-6",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "duration": "5",
    "sound": "false",
    "aspect_ratio": "1:1"
  }
}

Reference rule

Reference image: Upload up to 1 image file for image projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
duration	select	No	5	-	5, 10
sound	select	No	false	-	false, true
aspect_ratio	select	No	1:1	-	1:1, 16:9, 9:16

Kling 2.6 motion-control

kling-2-6-motion-controlAvailable via APIFiles API needed

Video · Dedicated motion-transfer project for driving one subject from one reference image plus one motion video. Use it when you want a cheaper Kling motion-control pass and can live without the extra scene controls in Kling 3.0 motion-control.

API guide Model page

Base credits

Modes

video-to-video

API input

Files API needed

Inputs

file

Prompt limit

2500 characters

Reference media

image, video · 2 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

No runnable Public API example is shown for this model.

Reference rule

Reference image + motion video: Upload exactly 1 character image and 1 motion clip. Both should clearly show the head, shoulders, and torso.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

File-based modes need /api/v1/files before they can be shown as complete API-ready examples. Files API

Parameters

key	Type	Required	Default	Range	Options
mode	select	No	720p	-	720p, 1080p
character_orientation	select	No	video	-	video, image

Kling V2.5 Turbo Pro

kling-v2-5-turbo-proAvailable via APIPartial: Files API needed

Video · Kuaishou's Kling V2.5 Turbo Pro video model, now supporting both text-to-video and image-to-video. Public pricing evidence clearly covers both text and image tiers at 5 seconds and 10 seconds, so Rivya maps it directly to 42 / 84 credits.

API guide Model page

Base credits

Modes

text-to-video, image-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

2500 characters

Reference media

image · 2 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "kling-v2-5-turbo-pro",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "duration": "5",
    "aspect_ratio": "16:9",
    "negative_prompt": "Describe what the video should avoid",
    "cfg_scale": 0.5
  }
}

Reference rule

Reference images: Optionally upload up to 2 images to switch into image-to-video mode; the second image maps to the tail frame.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
duration	select	No	5	-	5, 10
aspect_ratio	select	No	16:9	-	16:9, 9:16, 1:1
negative_prompt	text	No	-	-	-
cfg_scale	number	No	0.5	min 0 / max 1	-

Kling V2.1 Master

kling-v2-1-masterAvailable via APIPartial: Files API needed

Video · Kuaishou's older Kling V2.1 Master video model now supports both text-to-video and image-to-video on Rivya. Current pricing is 160 credits for 5 seconds and 320 credits for 10 seconds.

API guide Model page

Base credits

160

Modes

text-to-video, image-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

5000 characters

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "kling-v2-1-master",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "duration": "5",
    "aspect_ratio": "16:9",
    "negative_prompt": "Describe what the video should avoid",
    "cfg_scale": 0.5
  }
}

Reference rule

Reference image: Optionally upload one image to switch into image-to-video mode; leave it empty to stay in text mode.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
duration	select	No	5	-	5, 10
aspect_ratio	select	No	16:9	-	16:9, 9:16, 1:1
negative_prompt	text	No	-	-	-
cfg_scale	number	No	0.5	min 0 / max 1	-

Kling V2.1 Pro

kling-v2-1-proAvailable via APIFiles API needed

Video · Kuaishou's older Kling V2.1 Pro image-to-video model supports a first frame plus an optional tail frame image. Current pricing is 50 credits for 5 seconds and 100 credits for 10 seconds.

API guide Model page

Base credits

Modes

image-to-video

API input

Files API needed

Inputs

file

Prompt limit

5000 characters

Reference media

image · 2 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

No runnable Public API example is shown for this model.

Reference rule

Reference images: Image mode accepts up to 2 image files, and the second image maps to the tail frame.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

File-based modes need /api/v1/files before they can be shown as complete API-ready examples. Files API

Parameters

key	Type	Required	Default	Range	Options
duration	select	No	5	-	5, 10
negative_prompt	text	No	-	-	-
cfg_scale	number	No	0.5	min 0 / max 1	-

Kling V2.1 Standard

kling-v2-1-standardAvailable via APIFiles API needed

Video · Kuaishou's older Kling V2.1 Standard image-to-video model. Current pricing is 25 credits for 5 seconds and 50 credits for 10 seconds.

API guide Model page

Base credits

Modes

image-to-video

API input

Files API needed

Inputs

file

Prompt limit

5000 characters

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

No runnable Public API example is shown for this model.

Reference rule

Reference image: Image mode accepts up to 1 image file as the first frame.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

File-based modes need /api/v1/files before they can be shown as complete API-ready examples. Files API

Parameters

key	Type	Required	Default	Range	Options
duration	select	No	5	-	5, 10
negative_prompt	text	No	-	-	-
cfg_scale	number	No	0.5	min 0 / max 1	-

Kling AI Avatar Pro

kling-ai-avatar-proAvailable via APIFiles API needed

Video · Kuaishou's Kling AI Avatar Pro higher-quality talking-avatar model, using one portrait image plus one audio clip to generate lip-synced avatar video. Rivya currently prices it at a fixed 16 credits per generation.

API guide Model page

Base credits

Modes

image-to-video

API input

Files API needed

Inputs

file

Prompt limit

5000 characters

Reference media

image, audio · 2 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

No runnable Public API example is shown for this model.

Reference rule

Portrait image and audio: Upload one portrait image and one audio clip together.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

File-based modes need /api/v1/files before they can be shown as complete API-ready examples. Files API

Parameters

No extra model parameter is required.

Kling AI Avatar Standard

kling-ai-avatar-standardAvailable via APIFiles API needed

Video · Kuaishou's Kling AI Avatar Standard talking-avatar model, using one portrait image plus one audio clip to generate lip-synced avatar video. Rivya currently prices it at a fixed 8 credits per generation.

API guide Model page

Base credits

Modes

image-to-video

API input

Files API needed

Inputs

file

Prompt limit

5000 characters

Reference media

image, audio · 2 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

No runnable Public API example is shown for this model.

Reference rule

Portrait image and audio: Upload one portrait image and one audio clip together.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

File-based modes need /api/v1/files before they can be shown as complete API-ready examples. Files API

Parameters

No extra model parameter is required.

Infinitalk

infinitalkAvailable via APIFiles API needed

Video · Infinitalk is a portrait-plus-audio talking-video model. Current pricing is metered by resolution and audio duration: 480p = 3 credits per second and 720p = 12 credits per second.

API guide Model page

Base credits

Modes

image-to-video

API input

Files API needed

Inputs

file

Prompt limit

5000 characters

Reference media

image, audio · 2 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

No runnable Public API example is shown for this model.

Reference rule

Portrait image and audio: Upload one portrait image and one audio clip together.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

File-based modes need /api/v1/files before they can be shown as complete API-ready examples. Files API

Parameters

key	Type	Required	Default	Range	Options
resolution	select	No	480p	-	480p, 720p
seed	number	No	-	min 10000 / max 1000000	-

Runway

runwayAvailable via APIPartial: Files API needed

Video · Runway is a standalone video model that supports both text-to-video and image-to-video. Public pricing evidence currently confirms only 6 generation tiers, so Rivya keeps it on the verified set: `720p_5 = 12`, `720p_10 = 30`, and `1080p_5 = 30`.

API guide Model page

Base credits

Modes

text-to-video, image-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

1800 characters

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "runway",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "duration": "5",
    "quality": "720p",
    "aspectRatio": "16:9",
    "waterMark": "Leave empty to disable watermark"
  }
}

Reference rule

Reference image: Optionally upload one image to switch into image-to-video mode; leave it empty to stay in text mode.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
duration	select	No	5	-	5, 10
quality	select	No	720p	-	720p, 1080p
aspectRatio	select	No	16:9	-	16:9, 4:3, 1:1, 3:4, 9:16
waterMark	text	No	-	-	-

Runway Aleph

runway-alephAvailable via APIFiles API needed

Video · Source-video transformation project for reworking an existing clip into a new visual result. Use Aleph when the motion comes from your input footage and the creative direction comes from your prompt, with a fixed 90-credit price.

API guide Model page

Base credits

Modes

video-to-video

API input

Files API needed

Inputs

file

Prompt limit

5000 characters

Reference media

video, image · 2 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

No runnable Public API example is shown for this model.

Reference rule

Input media: Upload the source clip you want Aleph to transform. Add one optional still image only when you need extra style or subject guidance.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

File-based modes need /api/v1/files before they can be shown as complete API-ready examples. Files API

Parameters

key	Type	Required	Default	Range	Options
aspectRatio	select	No	16:9	-	16:9, 9:16, 4:3, 3:4, 1:1, 21:9
waterMark	text	No	-	-	-
seed	number	No	-	min 0 / max 2147483647	-

Luma Modify Video

luma-modify-videoAvailable via APIFiles API needed

Video · Standalone source-video rewrite project for pushing one existing clip into a new visual direction. Use it when the prompt should transform the footage itself, not just sharpen the export.

API guide Model page

Base credits

Modes

video-to-video

API input

Files API needed

Inputs

file

Prompt limit

Reference media

video · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

No runnable Public API example is shown for this model.

Reference rule

Input video: Upload one short source clip you want to transform. This option rewrites the footage instead of simply enhancing it.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

File-based modes need /api/v1/files before they can be shown as complete API-ready examples. Files API

Parameters

key	Type	Required	Default	Range	Options
watermark	text	No	-	-	-

Grok Imagine Video

grok-imagine-videoAvailable via APIPartial: Files API needed

Video · xAI's video model with Fun/Normal/Spicy creative modes and 5 aspect ratios. Unique style presets for different creative tones — from playful to cinematic to edgy.

API guide Model page

Base credits

Modes

text-to-video, image-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

5000 characters

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "grok-imagine-video",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "mode": "normal",
    "duration": 6,
    "resolution": "480p",
    "aspect_ratio": "2:3"
  }
}

Reference rule

Reference image: Upload up to 1 image file for image projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
mode	select	No	normal	-	fun, normal, spicy
duration	number	No	6	min 6 / max 30 / step 1	-
resolution	select	No	480p	-	480p, 720p
aspect_ratio	select	No	2:3	-	1:1, 16:9, 9:16, 2:3, 3:2

Sora 2 Pro

sora-2-proAvailable via APIPartial: Files API needed

Video · Sora 2's premium tier with Standard/High quality modes, 10s/15s clips, and watermark removal. Enhanced detail, lighting, and motion fidelity for professional video production.

API guide Model page

Base credits

Modes

text-to-video, image-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

10000 characters

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "sora-2-pro",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "size": "standard",
    "n_frames": "10",
    "aspect_ratio": "landscape",
    "remove_watermark": "false",
    "upload_method": "s3"
  }
}

Reference rule

Reference image: Upload up to 1 image file for image projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
size	select	No	-	-	standard, high
n_frames	select	No	10	-	10, 15
aspect_ratio	select	No	landscape	-	landscape, portrait
remove_watermark	select	No	false	-	false, true
upload_method	select	No	s3	-	s3, oss

Sora 2

sora-2Available via APIPartial: Files API needed

Video · OpenAI's video model for text-to-video and image-to-video with realistic world simulation, synced audio, 10s/15s clips, landscape/portrait outputs, and optional watermark removal.

API guide Model page

Base credits

Modes

text-to-video, image-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

10000 characters

Reference media

image · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "sora-2",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "n_frames": "10",
    "aspect_ratio": "landscape",
    "remove_watermark": "false",
    "upload_method": "s3"
  }
}

Reference rule

Reference image: Upload up to 1 image file for image projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
n_frames	select	No	10	-	10, 15
aspect_ratio	select	No	landscape	-	landscape, portrait
remove_watermark	select	No	false	-	false, true
upload_method	select	No	s3	-	s3, oss

Sora Watermark Remover

sora-watermark-removerAvailable via APIURL input ready

Video · Sora's watermark-removal post-processing model on Rivya for finished public Sora share links. Use it after the video is already done when the remaining task is watermark removal plus choosing S3 or OSS delivery.

API guide Model page

Base credits

Modes

video-to-video

API input

URL input ready

Inputs

url

Prompt limit

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "sora-watermark-remover",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "video_url": "https://sora.chatgpt.com/p/...",
    "upload_method": "s3"
  }
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

This model accepts public URL input through model parameters.

Parameters

key	Type	Required	Default	Range	Options
video_url	text	Yes	-	-	-
upload_method	select	Yes	s3	-	s3, oss

Topaz Video Upscaler

topaz-video-upscaleAvailable via APIFiles API needed

Video · Topaz's delivery-grade video upscaler on Rivya for approved clips that only need more clarity at export. Use it when the shot, motion, and timing are already right and the remaining problem is resolution or final-file sharpness.

API guide Model page

Base credits

Modes

video-to-video

API input

Files API needed

Inputs

file

Prompt limit

Reference media

video · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

No runnable Public API example is shown for this model.

Reference rule

Source video: Upload 1 source clip you want to preserve. This option improves delivery clarity rather than changing the shot.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

File-based modes need /api/v1/files before they can be shown as complete API-ready examples. Files API

Parameters

key	Type	Required	Default	Range	Options
upscale_factor	select	No	2	-	1, 2, 4

Veo3.1 Quality

veo3-1-qualityAvailable via APIPartial: Files API needed

Video · Google Veo 3.1's quality-first variant for premium text-to-video and image-led generation. Higher-fidelity visuals, stronger motion realism, and background audio by default make it Rivya's higher-end Veo option.

API guide Model page

Base credits

150

Modes

text-to-video, image-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

5000 characters

Reference media

image · 2 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "veo3-1-quality",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "aspectRatio": "16:9",
    "watermark": "Optional watermark text",
    "seeds": 10000,
    "enableTranslation": "true"
  }
}

Reference rule

Reference image: Upload up to 2 image files for the supported image-led project.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
aspectRatio	select	No	16:9	-	16:9, 9:16, Auto
watermark	text	No	-	-	-
seeds	number	No	-	min 10000 / max 99999 / step 1	-
enableTranslation	select	No	true	-	true, false

Veo3.1 Fast

veo3-1-fastAvailable via APIPartial: Files API needed

Video · Google Veo 3.1's fast variant with triple-mode support: text-to-video, image-to-video, and reference-to-video. Up to 3 reference images, native audio, and mode-aware aspect-ratio controls make it useful for quick cinematic clips.

API guide Model page

Base credits

Modes

text-to-video, image-to-video, reference-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

5000 characters

Reference media

image · 3 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "veo3-1-fast",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "generationType": "FIRST_AND_LAST_FRAMES_2_VIDEO",
    "aspectRatio": "16:9",
    "watermark": "Optional watermark text",
    "seeds": 10000,
    "enableTranslation": "true"
  }
}

Reference rule

Reference image: Upload up to 3 image files for image and reference-driven projects.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
generationType	select	No	FIRST_AND_LAST_FRAMES_2_VIDEO	-	FIRST_AND_LAST_FRAMES_2_VIDEO, REFERENCE_2_VIDEO
aspectRatio	select	No	16:9	-	16:9, 9:16, Auto
watermark	text	No	-	-	-
seeds	number	No	-	min 10000 / max 99999 / step 1	-
enableTranslation	select	No	true	-	true, false

Veo3.1 Lite

veo3-1-liteAvailable via APIPartial: Files API needed

Video · Google Veo 3.1's lowest-cost variant. Rivya currently exposes the smallest stable subset only: text-to-video and image-to-video at a fixed `10` credits per generation.

API guide Model page

Base credits

Modes

text-to-video, image-to-video

API input

Partial: Files API needed

Inputs

text, file

Prompt limit

5000 characters

Reference media

image · 2 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "veo3-1-lite",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "aspectRatio": "16:9",
    "watermark": "Optional watermark text",
    "seeds": 10000,
    "enableTranslation": "true"
  }
}

Reference rule

Reference image: Upload up to 2 image files for the supported image-driven project.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Prompt or URL modes may be callable now. Reference-media modes still need Files API upload support. Files API

Parameters

key	Type	Required	Default	Range	Options
aspectRatio	select	No	16:9	-	16:9, 9:16, Auto
watermark	text	No	-	-	-
seeds	number	No	-	min 10000 / max 99999 / step 1	-
enableTranslation	select	No	true	-	true, false

Suno Music

suno-musicAvailable via APIText input ready

Audio · Suno Music is Rivya's text-to-music model for turning one short brief into a first song draft with or without vocals. It keeps the fixed `12` credit entry point and exposes `Extend Music` as the next step after a successful track.

API guide Model page

Base credits

Modes

text-to-audio

API input

Text input ready

Inputs

text

Prompt limit

500 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "suno-music",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "model": "V4_5",
    "instrumental": "false"
  }
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Parameters

key	Type	Required	Default	Range	Options
model	select	No	V4_5	-	V4, V4_5, V4_5PLUS, V4_5ALL, V5, V5_5
instrumental	select	No	false	-	false, true

Suno Sounds

suno-soundsAvailable via APIText input ready

Audio · Suno Sounds is Rivya's lightweight text-to-sound model for ambience loops, background sound, and short sonic sketches. It keeps the documented fixed price of `3` credits per generation and lets successful results continue into `Vocal Separation`.

API guide Model page

Base credits

Modes

text-to-audio

API input

Text input ready

Inputs

text

Prompt limit

500 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "suno-sounds",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "model": "V5",
    "soundLoop": "false",
    "soundTempo": 1,
    "soundKey": "Any"
  }
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Parameters

key	Type	Required	Default	Range	Options
model	select	No	V5	-	V5, V5_5
soundLoop	select	No	false	-	false, true
soundTempo	number	No	-	min 1 / max 300 / step 1	-
soundKey	select	No	Any	-	Any, Cm, C#m, Dm, D#m, Em, Fm, F#m, Gm, G#m, Am, A#m, Bm, C, C#, D, D#, E, F, F#, G, G#, A, A#, B

Suno Lyrics

suno-lyricsAvailable via APIText input ready

Audio · Suno Lyrics is Rivya's lyric-generation model for turning one theme or mood into song words at a fixed cost of `1` credit per request.

API guide Model page

Base credits

Modes

text-to-audio

API input

Text input ready

Inputs

text

Prompt limit

200 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "suno-lyrics",
  "prompt": "A clean editorial product image on a soft studio background"
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Parameters

No extra model parameter is required.

ElevenLabs Dialogue V3

elevenlabs-dialogue-v3Available via APIText input ready

Audio · ElevenLabs' multi-speaker dialogue model on Rivya. It is built for role-based speech generation, with individual voice assignments, stability controls, and dialogue-ready pacing for podcasts, interviews, and character scenes.

API guide Model page

Base credits

Modes

dialogue-to-audio

API input

Text input ready

Inputs

text

Prompt limit

5000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "elevenlabs-dialogue-v3",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "default_voice": "Adam",
    "stability": "0.5"
  }
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Parameters

key	Type	Required	Default	Range	Options
default_voice	select	No	Adam	-	Adam, Alice, Bill, Brian, Callum, Charlie, Chris, Daniel, Eric, George, Harry, Jessica, Laura, Liam, Lily, Matilda, River, Roger, Sarah, Will
stability	select	No	0.5	-	0, 0.5, 1
language_code	text	No	-	-	-

ElevenLabs Turbo 2.5

elevenlabs-turbo-2-5Available via APIText input ready

Audio · ElevenLabs' fast text-to-speech model on Rivya. With low-latency voice generation and adjustable stability, similarity, style, and speed, it is built for rapid voiceover drafts and interactive TTS projects.

API guide Model page

Base credits

Modes

text-to-speech

API input

Text input ready

Inputs

text

Prompt limit

5000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "elevenlabs-turbo-2-5",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "voice": "TX3LPaxmHKxFdv7VOQHJ",
    "stability": 0.5,
    "similarity_boost": 0.75,
    "style": 0,
    "speed": 1,
    "timestamps": "false",
    "previous_text": "Optional context before this line",
    "next_text": "Optional context after this line",
    "language_code": "Optional locale code like en or zh"
  }
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Parameters

key	Type	Required	Default	Range	Options
voice	select	Yes	TX3LPaxmHKxFdv7VOQHJ	-	TX3LPaxmHKxFdv7VOQHJ, cgSgspJ2msm6clMCkdW9, pNInz6obpgDQGcFmaJgB, BIvP0GN1cAtSRTxNHnWS, aMSt68OGf4xUZAnLpTU8
stability	number	No	0.5	min 0 / max 1 / step 0.05	-
similarity_boost	number	No	0.75	min 0 / max 1 / step 0.05	-
style	number	No	0	min 0 / max 1 / step 0.05	-
speed	number	No	1	min 0.7 / max 1.2 / step 0.05	-
timestamps	select	No	false	-	false, true
previous_text	text	No	-	-	-
next_text	text	No	-	-	-
language_code	text	No	-	-	-

ElevenLabs Multilingual V2

elevenlabs-multilingual-v2Available via APIText input ready

Audio · ElevenLabs' multilingual text-to-speech model on Rivya, supporting about 30 languages with auto-detection. It is the stronger option for localization, cross-language delivery, and more natural multilingual voiceovers.

API guide Model page

Base credits

Modes

text-to-speech

API input

Text input ready

Inputs

text

Prompt limit

5000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "elevenlabs-multilingual-v2",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "voice": "TX3LPaxmHKxFdv7VOQHJ",
    "stability": 0.5,
    "similarity_boost": 0.75,
    "style": 0,
    "speed": 1,
    "timestamps": "false"
  }
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Parameters

key	Type	Required	Default	Range	Options
voice	select	Yes	TX3LPaxmHKxFdv7VOQHJ	-	TX3LPaxmHKxFdv7VOQHJ, cgSgspJ2msm6clMCkdW9, pNInz6obpgDQGcFmaJgB, BIvP0GN1cAtSRTxNHnWS, aMSt68OGf4xUZAnLpTU8
stability	number	No	0.5	min 0 / max 1 / step 0.05	-
similarity_boost	number	No	0.75	min 0 / max 1 / step 0.05	-
style	number	No	0	min 0 / max 1 / step 0.05	-
speed	number	No	1	min 0.7 / max 1.2 / step 0.05	-
timestamps	select	No	false	-	false, true
previous_text	text	No	-	-	-
next_text	text	No	-	-	-
language_code	text	No	-	-	-

ElevenLabs Sound Effect V2

elevenlabs-sound-effect-v2Available via APIText input ready

Audio · ElevenLabs' text-to-sound model on Rivya for short effects, transitions, and ambience loops. Generate 0.5–22 second audio clips with adjustable prompt influence, loop mode, and 19 output formats for editing, product, or game projects.

API guide Model page

Base credits

Modes

text-to-audio

API input

Text input ready

Inputs

text

Prompt limit

5000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "elevenlabs-sound-effect-v2",
  "prompt": "A clean editorial product image on a soft studio background",
  "params": {
    "loop": "false",
    "duration_seconds": 3,
    "prompt_influence": 0.3,
    "output_format": "mp3_44100_128"
  }
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Parameters

key	Type	Required	Default	Range	Options
loop	select	No	false	-	false, true
duration_seconds	number	No	3	min 0.5 / max 22 / step 0.5	-
prompt_influence	number	No	0.3	min 0 / max 1 / step 0.05	-
output_format	select	No	mp3_44100_128	-	mp3_22050_32, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, pcm_8000, pcm_16000, pcm_22050, pcm_24000, pcm_44100, pcm_48000, ulaw_8000, alaw_8000, opus_48000_32, opus_48000_64, opus_48000_96, opus_48000_128, opus_48000_192

ElevenLabs Audio Isolation

elevenlabs-audio-isolationAvailable via APIFiles API needed

Audio · ElevenLabs' audio cleanup and voice-isolation model on Rivya. Upload one recording to isolate vocals, remove background noise, and clean spoken audio before editing or publishing.

API guide Model page

Base credits

Modes

audio-to-audio

API input

Files API needed

Inputs

file

Prompt limit

Reference media

audio · 1 file(s)

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

No runnable Public API example is shown for this model.

Reference rule

Source audio: Upload one audio file and Rivya will isolate and clean the target track.

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

File-based modes need /api/v1/files before they can be shown as complete API-ready examples. Files API

Parameters

No extra model parameter is required.

GPT-5.5

gpt-5-5-chatAvailable via APIText input ready

Chat · OpenAI's advanced GPT chat model on Rivya for complex reasoning, image-aware analysis, research synthesis, and structured writing when the brief needs more room.

API guide Model page

Base credits

Modes

responses

API input

Text input ready

Inputs

text, file

Prompt limit

20000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "gpt-5-5-chat",
  "prompt": "A clean editorial product image on a soft studio background"
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Chat API supports non-streaming and SSE streaming turns in Public API v1. Image attachments must use Files API file_id values.

Parameters

No extra model parameter is required.

GPT-5.4

gpt-5-4-chatAvailable via APIText input ready

Chat · OpenAI's higher-end AI chat model on Rivya, with stronger structured input handling, reasoning control, and tool-oriented conversation projects for more complex analysis and writing tasks.

API guide Model page

Base credits

Modes

responses

API input

Text input ready

Inputs

text, file

Prompt limit

20000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "gpt-5-4-chat",
  "prompt": "A clean editorial product image on a soft studio background"
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Chat API supports non-streaming and SSE streaming turns in Public API v1. Image attachments must use Files API file_id values.

Parameters

No extra model parameter is required.

GPT-5.4 Codex

gpt-5.4-codex-chatAvailable via APIText input ready

Chat · OpenAI's higher-end Codex model on Rivya, with stronger coding, structured reasoning, and tool-oriented collaboration for demanding repo-scale development projects.

API guide Model page

Base credits

Modes

responses

API input

Text input ready

Inputs

text, file

Prompt limit

20000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "gpt-5.4-codex-chat",
  "prompt": "A clean editorial product image on a soft studio background"
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Chat API supports non-streaming and SSE streaming turns in Public API v1. Image attachments must use Files API file_id values.

Parameters

No extra model parameter is required.

GPT-5.3 Codex

gpt-5-3-codex-chatAvailable via APIText input ready

Chat · OpenAI's latest and most capable Codex model on Rivya. It combines state-of-the-art code generation with deeper agentic reasoning for the most demanding development projects.

API guide Model page

Base credits

Modes

responses

API input

Text input ready

Inputs

text, file

Prompt limit

20000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "gpt-5-3-codex-chat",
  "prompt": "A clean editorial product image on a soft studio background"
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Chat API supports non-streaming and SSE streaming turns in Public API v1. Image attachments must use Files API file_id values.

Parameters

No extra model parameter is required.

GPT-5.2

gpt-5-2-chatAvailable via APIText input ready

Chat · OpenAI's flagship AI chat model on Rivya, with advanced reasoning, vision support for up to 6 images, and a 20K-character context window. It is a strong general GPT option for research, planning, writing, and image-aware analysis.

API guide Model page

Base credits

Modes

chat-completion

API input

Text input ready

Inputs

text, file

Prompt limit

20000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "gpt-5-2-chat",
  "prompt": "A clean editorial product image on a soft studio background"
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Chat API supports non-streaming and SSE streaming turns in Public API v1. Image attachments must use Files API file_id values.

Parameters

No extra model parameter is required.

GPT-5.2 Codex

gpt-5-2-codex-chatAvailable via APIText input ready

Chat · OpenAI's more advanced Codex model on Rivya, with stronger reasoning for complex engineering tasks. It is optimized for long-horizon agentic coding, architecture decisions, and larger refactors where plain code generation is not enough.

API guide Model page

Base credits

Modes

responses

API input

Text input ready

Inputs

text, file

Prompt limit

20000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "gpt-5-2-codex-chat",
  "prompt": "A clean editorial product image on a soft studio background"
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Chat API supports non-streaming and SSE streaming turns in Public API v1. Image attachments must use Files API file_id values.

Parameters

No extra model parameter is required.

GPT-5.1 Codex

gpt-5-1-codex-chatAvailable via APIText input ready

Chat · OpenAI's upgraded Codex model on Rivya, with improved code accuracy and stronger reasoning for agentic coding tasks. It keeps the same long-output, repo-aware project while improving multi-file refactors and safer code edits.

API guide Model page

Base credits

Modes

responses

API input

Text input ready

Inputs

text, file

Prompt limit

20000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "gpt-5-1-codex-chat",
  "prompt": "A clean editorial product image on a soft studio background"
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Chat API supports non-streaming and SSE streaming turns in Public API v1. Image attachments must use Files API file_id values.

Parameters

No extra model parameter is required.

GPT-5 Codex

gpt-5-codex-chatAvailable via APIText input ready

Chat · OpenAI's code-specialized GPT-5 Codex model on Rivya for debugging, implementation planning, refactors, and technical problem-solving with vision support.

API guide Model page

Base credits

Modes

responses

API input

Text input ready

Inputs

text, file

Prompt limit

20000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "gpt-5-codex-chat",
  "prompt": "A clean editorial product image on a soft studio background"
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Chat API supports non-streaming and SSE streaming turns in Public API v1. Image attachments must use Files API file_id values.

Parameters

No extra model parameter is required.

Gemini 3.1 Pro

gemini-3-1-pro-chatAvailable via APIText input ready

Chat · Google's latest and most capable Gemini AI chat model on Rivya. With top-tier reasoning, vision, and instruction following, it is the strongest Gemini option for demanding analytical and creative tasks.

API guide Model page

Base credits

Modes

chat-completion

API input

Text input ready

Inputs

text, file

Prompt limit

20000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "gemini-3-1-pro-chat",
  "prompt": "A clean editorial product image on a soft studio background"
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Chat API supports non-streaming and SSE streaming turns in Public API v1. Image attachments must use Files API file_id values.

Parameters

No extra model parameter is required.

Gemini 3 Pro

gemini-3-pro-chatAvailable via APIText input ready

Chat · Google's higher-depth Gemini AI chat model on Rivya. With stronger reasoning than Gemini 2.5 Pro and vision support, it is better suited to research synthesis, technical writing, and more deliberate multimodal analysis.

API guide Model page

Base credits

Modes

chat-completion

API input

Text input ready

Inputs

text, file

Prompt limit

20000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "gemini-3-pro-chat",
  "prompt": "A clean editorial product image on a soft studio background"
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Chat API supports non-streaming and SSE streaming turns in Public API v1. Image attachments must use Files API file_id values.

Parameters

No extra model parameter is required.

Gemini 3 Flash

gemini-3-flash-chatAvailable via APIText input ready

Chat · Google's next-gen fast AI chat model on Rivya. With even lower token costs than Gemini 2.5 Flash and stronger reasoning, it is built for high-volume multimodal chat, screenshot triage, and rapid assistant work.

API guide Model page

Base credits

Modes

chat-completion

API input

Text input ready

Inputs

text, file

Prompt limit

20000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "gemini-3-flash-chat",
  "prompt": "A clean editorial product image on a soft studio background"
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Chat API supports non-streaming and SSE streaming turns in Public API v1. Image attachments must use Files API file_id values.

Parameters

No extra model parameter is required.

Gemini 2.5 Pro

gemini-2-5-pro-chatAvailable via APIText input ready

Chat · Google's more advanced Gemini AI chat model on Rivya. Stronger reasoning than Flash with vision support and 20K context, it is the better fit for research synthesis, document analysis, and structured writing at 2 credits.

API guide Model page

Base credits

Modes

chat-completion

API input

Text input ready

Inputs

text, file

Prompt limit

20000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "gemini-2-5-pro-chat",
  "prompt": "A clean editorial product image on a soft studio background"
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Chat API supports non-streaming and SSE streaming turns in Public API v1. Image attachments must use Files API file_id values.

Parameters

No extra model parameter is required.

Gemini 2.5 Flash

gemini-2-5-flash-chatAvailable via APIText input ready

Chat · Google's fastest and most affordable AI chat model on Rivya. At 1 credit per use with vision support for up to 6 images, it fits quick Q&A, first-pass summaries, screenshot triage, and everyday AI assistance.

API guide Model page

Base credits

Modes

chat-completion

API input

Text input ready

Inputs

text, file

Prompt limit

20000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "gemini-2-5-flash-chat",
  "prompt": "A clean editorial product image on a soft studio background"
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Chat API supports non-streaming and SSE streaming turns in Public API v1. Image attachments must use Files API file_id values.

Parameters

No extra model parameter is required.

Claude Opus 4.7

claude-opus-4-7-chatAvailable via APIText input ready

Chat · Anthropic's flagship Claude chat model on Rivya for deep reasoning, careful synthesis, executive writing, and high-impact text work.

API guide Model page

Base credits

Modes

chat-completion

API input

Text input ready

Inputs

text

Prompt limit

20000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "claude-opus-4-7-chat",
  "prompt": "A clean editorial product image on a soft studio background"
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Chat API supports non-streaming and SSE streaming turns in Public API v1. Image attachments are not supported for this chat model.

Parameters

No extra model parameter is required.

Claude Opus 4.6

claude-opus-4-6-chatAvailable via APIText input ready

Chat · Anthropic's flagship Claude AI chat model on Rivya. It is built for deep reasoning, complex analysis, and high-quality writing in demanding, high-stakes projects.

API guide Model page

Base credits

Modes

chat-completion

API input

Text input ready

Inputs

text

Prompt limit

20000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "claude-opus-4-6-chat",
  "prompt": "A clean editorial product image on a soft studio background"
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Chat API supports non-streaming and SSE streaming turns in Public API v1. Image attachments are not supported for this chat model.

Parameters

No extra model parameter is required.

Claude Sonnet 4.6

claude-sonnet-4-6-chatAvailable via APIText input ready

Chat · Anthropic's balanced Claude AI chat model on Rivya. It keeps strong long-form reasoning and careful analysis for content, research, and coding projects without jumping to Opus-level spend.

API guide Model page

Base credits

Modes

chat-completion

API input

Text input ready

Inputs

text

Prompt limit

20000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "claude-sonnet-4-6-chat",
  "prompt": "A clean editorial product image on a soft studio background"
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Chat API supports non-streaming and SSE streaming turns in Public API v1. Image attachments are not supported for this chat model.

Parameters

No extra model parameter is required.

Claude Opus 4.5

claude-opus-4-5-chatAvailable via APIText input ready

Chat · Anthropic's flagship Claude AI chat model on Rivya. It is exceptional at deep reasoning, complex analysis, and expert-level writing, making it a premium choice for mission-critical AI tasks.

API guide Model page

Base credits

Modes

chat-completion

API input

Text input ready

Inputs

text

Prompt limit

20000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "claude-opus-4-5-chat",
  "prompt": "A clean editorial product image on a soft studio background"
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Chat API supports non-streaming and SSE streaming turns in Public API v1. Image attachments are not supported for this chat model.

Parameters

No extra model parameter is required.

Claude Sonnet 4.5

claude-sonnet-4-5-chatAvailable via APIText input ready

Chat · Anthropic's balanced Claude AI chat model on Rivya. It is strong at nuanced writing, careful analysis, and safety-conscious responses, making it a strong Claude option for content creation and research.

API guide Model page

Base credits

Modes

chat-completion

API input

Text input ready

Inputs

text

Prompt limit

20000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "claude-sonnet-4-5-chat",
  "prompt": "A clean editorial product image on a soft studio background"
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Chat API supports non-streaming and SSE streaming turns in Public API v1. Image attachments are not supported for this chat model.

Parameters

No extra model parameter is required.

Claude Haiku 4.5

claude-haiku-4-5-chatAvailable via APIText input ready

Chat · Anthropic's lightweight Claude AI chat model on Rivya. It is tuned for speed, cost efficiency, and stable day-to-day chat performance in high-frequency projects where you want Claude tone without premium spend.

API guide Model page

Base credits

Modes

chat-completion

API input

Text input ready

Inputs

text

Prompt limit

20000 characters

Reference media

Request

POST /api/v1/generations

Auth

Bearer API key

Idempotency-Key

Recommended

Body

{
  "model": "claude-haiku-4-5-chat",
  "prompt": "A clean editorial product image on a soft studio background"
}

Reference rule

Result

The create response returns a public task id. Poll GET /api/v1/generations/{taskId} until the status is succeeded or failed.

Common errors

validation_failed, insufficient_credits, idempotency_conflict, not_found

Chat API supports non-streaming and SSE streaming turns in Public API v1. Image attachments are not supported for this chat model.

Parameters

No extra model parameter is required.

Model API Reference

How To Read This Reference

Request Pattern

Dynamic Model Reference

Use this reference with the debugger

Z-Image

Body

Parameters

Nano Banana 2

Body

Parameters

Nano Banana Pro

Body

Parameters

Nano Banana

Body

Parameters

GPT Image 2

Body

Parameters

GPT Image 1.5

Body

Parameters

4o Image

Body

Parameters

Seedream 5.0 Lite

Body

Parameters

Seedream 4.5

Body

Parameters

Seedream 4.0

Body

Parameters

Seedream 3.0

Body

Parameters

Grok Imagine

Body

Parameters

Flux 2 Pro

Body

Parameters

Flux 2 Flex

Body

Parameters

Flux Kontext Max

Body

Parameters

Flux Kontext Pro

Body

Parameters

Qwen2 Image

Body

Parameters

Qwen Image

Body

Parameters

Midjourney

Body

Parameters

Recraft Remove Background

Body

Parameters

Recraft Crisp Upscale

Body

Parameters

Wan 2.7 Image Pro

Body

Parameters

Wan 2.7 Image

Body

Parameters

Google Imagen4 Ultra

Body

Parameters

Google Imagen4

Body

Parameters