ideogram_generate | Images from a text prompt | ideogram-3 (default), ideogram-4-5, ideogram-4, ideogram-3-character, ideogram-3-custom-model, ideogram-4-custom-model, ideogram-3-transparent, ideogram-4-transparent, ideogram-2a, ideogram-2, gpt-image-2, gpt-image-2-5-flare, gpt-image-2-5-sunburst, nano-banana-2, nano-banana-pro, p-image-ideogram, z-image, auto |
ideogram_precise_edit | Edit an image at its exact size: a prompt, an optional mask (black = edit), up to 4 reference images, context_window to confine the edit | ideogram-4-5 |
ideogram_inpaint | Repaint the masked part of an image (black = repaint) | ideogram-3 (default), ideogram-3-character, ideogram-3-custom-model |
ideogram_edit | The 1.x name of ideogram_inpaint (kept through 2.x) | as inpaint |
ideogram_remix | New images from a source image and a prompt | ideogram-3 (default), ideogram-3-character, ideogram-3-custom-model, ideogram-4, auto |
ideogram_reframe | Extend an image to a new size (outpainting) | ideogram-3 (default), nano-banana-2 |
ideogram_replace_background | A new background, the subject kept | ideogram-3 (default), gpt-image-2 |
ideogram_remove_background | The foreground as a transparent PNG | ideogram-1 |
ideogram_remove_object | Remove what the mask marks (white = remove) and fill the gap | ideogram-1 |
ideogram_upscale | Enlarge an image | auto (default), topaz-bloom-2, topaz-redefine, topaz-standard-2, topaz-text-refine, topaz-wonder-3-5, nano-banana-pro |
ideogram_describe | Describe an image: words (ideogram-3, default) or a structured JSON prompt (ideogram-4) | ideogram-3, ideogram-4 |
ideogram_video_text | A video from a prompt: duration, aspect ratio, resolution, audio per model; saved as mp4 (give duration: omitted, Seedance is quoted at its maximum length) | seedance-2-5-text-to-video (default), seedance-2-text-to-video, kling-3-standard-text-to-video, minimax-h3-text-to-video |
ideogram_video_image | A video from a start image (and an end image): files, URLs or assets | seedance-2-5-image-to-video (default), seedance-2-image-to-video, kling-3-standard-image-to-video, minimax-h3-image-to-video |
ideogram_video_reference | A video guided by reference images, MP3/WAV clips (2-30 s on Seedance 2.5, 2-15 s elsewhere) and videos stored with Ideogram, in prompt order; at least one reference image or video | seedance-2-5-reference-to-video (default), seedance-2-reference-to-video, minimax-h3-reference-to-video |
ideogram_layerize | A flat image as an editable design: the text-free base image (saved) and the detected text blocks (JSON: text, position, font, size, colour); optional font_candidate_files (.ttf, .otf, .woff, .woff2) to match against | ideogram-3 |
ideogram_ad_localizer | Translate an ad's copy into one language, keeping layout, logos and product; exact_copy pins wordings | one operation (post_ad_localizer) |
ideogram_ad_resizer | Reframe an ad to a platform's exact ad size inside its safe zone | one operation (post_ad_resizer) |
ideogram_ad_variations | Vary an ad along one axis: people, setting, group_size or scene | one operation (post_ad_variations) |
ideogram_colorways | Recolor a product photo: up to 4 masks paired with hex colours | one operation (post_colorways) |
ideogram_ghost_mannequin | A garment on an invisible mannequin from its photos, in the view asked | one operation (post_ghost_mannequin) |
ideogram_material_swap | Apply reference materials to the masked regions of a product photo | one operation (post_material_swap) |
ideogram_model_pose_variants | Re-pose the model of a fashion image by instruction | one operation (post_model_pose_variants) |
ideogram_sketch_to_render | Render a fashion sketch as a product photo | one operation (post_sketch_to_render) |
ideogram_magic_prompt | Rewrite a prompt into an Ideogram 4.0 structured JSON prompt (nothing generated) | one operation (post_magic_prompt_v4) |
ideogram_layerize_logos | Detect and remove reference logos from a flat design: the base image saved, the layers listed | one operation (post_layerize_logos) |
ideogram_provenance | Check whether an image was created by Ideogram (free) | one operation (post_provenance_verify) |
ideogram_snap_mask | Snap a hand-drawn mask to the object it marks; the PNG saved | one operation (post_snap_mask) |
ideogram_quote | The price of a call: {"tool": "ideogram_generate", "arguments": {…}} | every operation that offers a dry run (not describe, ad variations, pose variants, sketch to render, nor the v1 utilities) |
ideogram_generation | Collect a generation by generation_id — its images or its video | — |
ideogram_usage | Billed usage as Ideogram reports it: buckets of line items summed per product and currency, the buckets handed on (the shape ai-cost reads); default the last 7 days by day | — |
ideogram_invoices | The organization's invoices with their line items (organization-admin key) | — |
ideogram_api_keys | The organization's API keys, redacted (organization-admin key) | — |
ideogram_datasets | Your training datasets: the list (searched by name) or one with its files and models | — |
ideogram_dataset_upload | Images, .txt captions and .zip archives into a dataset (an existing one, or a new one from a name); local paths or public https URLs | — |
ideogram_train | Train a custom model from a dataset of 15–100 images; hyperparameters route to the advanced operation | ideogram-4 (default), ideogram-3 |
ideogram_models | Your custom models and the shared ones, or one with its training runs; a completed model's custom_model_uri generates through ideogram_generate | — |
ideogram_operations | What the API offers: families, operations, fields, limits | — |
ideogram_api | Any served operation by id, including the ones the documentation index does not list (the reframe models auto, bria-expand, gpt-image-2-5-flare, nano-banana-pro) | — |