Flux Kontext Max API reference
Check Flux Kontext Max availability, inputs, parameters, file requirements, credit pricing, and request examples for Rivya Public API v1. Model ID: flux-kontext-max.
flux-kontext-max
text, file
Required for reference modes
Credit rate: 8 per image The final cost is rounded up to whole credits.
Image
FIXED
No documented prompt limit
Request fields
Set model at the top level. Put model-specific controls and reference inputs in params, using the format documented for this model.
| Key | Type | Required | Default | Description |
|---|---|---|---|---|
| model | string | Yes | flux-kontext-max | Set model to flux-kontext-max. |
| prompt | string | Yes | - | Prompt text for models that support text input. |
| params | object | No | - | The model-specific params object. Use the documented keys and reference-file format for this model. |
| client_request_id | string | No | - | Optional ID for tracing this request in your system. It does not replace Idempotency-Key. |
Model parameters
| Key | Type | Required | Default | Range | Options | Description |
|---|---|---|---|---|---|---|
| aspectRatio | select | No | 16:9 | - | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | Aspect ratio |
| outputFormat | select | No | jpeg | - | jpeg, png | Choose JPEG or PNG. PNG does not by itself create a transparent background. |
| enableTranslation | select | No | true | - | true, false | Translate prompt to English |
| promptUpsampling | select | No | false | - | false, true | Ask the provider to expand your prompt before generating. Added details may change how it interprets your instruction. |
| safetyTolerance | number | No | 2 | min 0 / max 6 | - | Lower values apply stricter content filtering. Use an integer from 0 to 6 for generation, or up to 2 when editing an image. Content rules still apply. |
| watermark | text | No | - | - | - | Watermark |
Upload policy
Upload reference files through Files API first. Keep the original URLs, verified metadata, and tokens. Follow this model's request example: some models use params.referenceMediaItems, while others use different fields.
Reference image: Add up to 1 source image for editing. JPEG, PNG, or WebP; up to 10 MiB.
1
image
When duration verification is required, use duration_token from /api/v1/files as durationToken in the request. Keep any additional signed metadata this model requires.
| kind | Max size | MIME types |
|---|---|---|
| image | 10 MB | image/jpeg, image/png, image/webp |
Minimal request
{
"model": "flux-kontext-max",
"prompt": "A product bottle on a light gray background, lit softly from the left.",
"params": {
"aspectRatio": "16:9",
"outputFormat": "jpeg",
"enableTranslation": "true",
"promptUpsampling": "false",
"safetyTolerance": 2,
"watermark": "Optional watermark identifier"
}
}Reference-file request
{
"model": "flux-kontext-max",
"prompt": "A product bottle on a light gray background, lit softly from the left.",
"params": {
"aspectRatio": "16:9",
"outputFormat": "jpeg",
"enableTranslation": "true",
"promptUpsampling": "false",
"safetyTolerance": 2,
"watermark": "Optional watermark identifier",
"referenceMediaItems": [
{
"url": "https://cdn.example.com/reference-image.png",
"kind": "image",
"name": "reference-image.png",
"mimeType": "image/png"
}
]
}
}Example response
An accepted generation request returns a task ID. Poll the status endpoint until the task succeeds or fails. A status request failure does not mean generation failed.
{
"id": "task_flux_kontext_max_example",
"status": "queued",
"model": "flux-kontext-max",
"reserved_credits": 8,
"final_credits": 0,
"settlement_status": "RESERVED",
"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.
