Rivya AI Docs

Flux Kontext Pro API Integration

Use Flux Kontext Pro through Rivya Public API v1 with model id flux-kontext-pro, supported inputs, parameters, Files API rules, credits, and response examples.

Available via APIText or URL ready; reference modes use Files APIImage
API model id

flux-kontext-pro

Inputs

text, file

Files API

Required for reference modes

Base credits

4

Capability

Image

Billing

FIXED

Prompt limit

No documented prompt limit

Request contract

Send the model id at the top level. Model-specific controls belong in params.

KeyTypeRequiredDefaultDescription
modelstringYesflux-kontext-proUse the flux-kontext-pro API model id.
promptstringYes-Prompt text for models that support text input.
paramsobjectNo-Model-specific parameter object. Use the rows below for allowed keys.
client_request_idstringNo-Optional client-side id for tracing requests in your system.

Model parameters

KeyTypeRequiredDefaultRangeOptionsDescription
aspectRatioselectNo16:9-21:9, 16:9, 4:3, 1:1, 3:4, 9:16Aspect ratio
outputFormatselectNojpeg-jpeg, pngJPEG is smaller, while PNG is better for transparency or cleaner lossless edges.
enableTranslationselectNotrue-true, falseAuto-translate prompt
promptUpsamplingselectNofalse-false, trueWhen enabled, Rivya lets the model expand and polish your prompt before generation. It often helps detail quality, but can also make the result more interpretive than your raw prompt.
safetyTolerancenumberNo2min 0 / max 6-Controls how strict the content moderation is. Generation usually allows a wider range than editing; lower values are stricter and higher values are more permissive.
watermarktextNo---Watermark

Upload policy

Upload reference files first, then place the returned URL and duration token inside params.referenceMediaItems.

Reference rule

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

Max files

1

Accepted file kinds

image

Duration token

Video and audio references should carry durationToken from /api/v1/files when duration verification is required.

kindMax sizeMIME types
image10 MBimage/jpeg, image/png, image/webp

Minimal request

{
  "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-file request

{
  "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",
    "referenceMediaItems": [
      {
        "url": "https://cdn.example.com/reference-image.png",
        "kind": "image",
        "name": "reference-image.png",
        "mimeType": "image/png"
      }
    ]
  }
}

Create response

The create endpoint returns a public task id. Poll the status endpoint until the task succeeds or fails.

{
  "id": "task_flux_kontext_pro_example",
  "status": "queued",
  "model": "flux-kontext-pro",
  "reserved_credits": 4,
  "final_credits": 0,
  "created_at": "2026-05-11T00:00:00.000Z",
  "updated_at": "2026-05-11T00:00:00.000Z",
  "result": null,
  "error": null
}

Common errors

validation_failed, insufficient_credits, idempotency_conflict, rate_limited, not_found

Some modes require Files API reference uploads.