↓
Rivya AI Docs
Model API guides

Ideogram V3 Remix API reference

Check Ideogram V3 Remix availability, inputs, parameters, file requirements, credit pricing, and request examples for Rivya Public API v1. Model ID: ideogram-v3-remix.

Available via APIAPI statusImage
API model ID

ideogram-v3-remix

Inputs

file

Files API

Required for reference modes

Credit pricing

Credit rate: 3.5–10 per image The final cost is rounded up to whole credits.

Capability

Image

Billing

FIXED

Prompt limit

5000 characters

Request fields

Set model at the top level. Put model-specific controls and reference inputs in params, using the format documented for this model.

KeyTypeRequiredDefaultDescription
modelstringYesideogram-v3-remixSet model to ideogram-v3-remix.
promptstringYes-Maximum 5000 characters for this model.
paramsobjectYes-The model-specific params object. Use the documented keys and reference-file format for this model.
client_request_idstringNo-Optional ID for tracing this request in your system. It does not replace Idempotency-Key.

Model parameters

KeyTypeRequiredDefaultRangeOptionsDescription
rendering_speedselectNoBALANCED-TURBO, BALANCED, QUALITYBalances speed, cost, and detail. Turbo is the fastest and cheapest, Quality is the most detailed and most expensive, and Balanced is the default middle ground.
styleselectNoAUTO-AUTO, GENERAL, REALISTIC, DESIGNStyle
expand_promptselectNotrue-true, falseIdeogram's prompt expansion switch. Turning it on helps the model flesh out your description; turning it off is better when you want tight prompt control.
image_sizeselectNosquare_hd-square, square_hd, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9Image size
num_imagesselectNo1-1, 2, 3, 4Choose 1–4 outputs. The total is the per-image rate multiplied by the selected count, rounded up to whole credits.
seednumberNo---Keep the prompt, reference inputs, and settings unchanged when reusing a seed. Allowed seed values and defaults depend on the model, and identical results are not guaranteed.
strengthnumberNo0.8min 0.01 / max 1-Controls how strongly the source image shapes the result. Higher values stay closer to the original structure, while lower values allow more deviation.
negative_prompttextNo---Negative prompt

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 rule

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

Max files

1

Accepted file kinds

image

Duration token

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.

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

No runnable Public API example is shown for this model.

Reference-file request

{
  "model": "ideogram-v3-remix",
  "prompt": "A product bottle on a light gray background, lit softly from the left.",
  "params": {
    "rendering_speed": "BALANCED",
    "style": "AUTO",
    "expand_prompt": "true",
    "image_size": "square_hd",
    "num_images": "1",
    "seed": 1,
    "strength": 0.8,
    "negative_prompt": "Optional things to avoid",
    "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_ideogram_v3_remix_example",
  "status": "queued",
  "model": "ideogram-v3-remix",
  "reserved_credits": 7,
  "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.