Claude Imagine

Return one of the caller's own image or video generations by task id: a finished one again (no new generation, no credits), or wait for one that was still running. Task ids are quoted in every generation reply and by list_generations. Free to call; it never starts anything.

Edit an existing image with a text instruction, using Claude Imagine credits. Pass the full-resolution URL of the image to change, plus up to 8 more images when the result should combine them, such as a person placed into a scene, a garment put on a model or a product set in a new setting. Pass them as separate URLs; do not stitch them into one collage. The result is a new image, and the originals are untouched. Say in the prompt what must stay the same, not only what changes.

Generate an AI image from a text prompt using Claude Imagine credits. Returns the image inline plus its full-resolution URL. To change an existing image, use edit_image. For a YouTube thumbnail, book cover, album or podcast cover, poster, blog cover or product photo, call list_styles first and pass one of its ids as style.

Generate an AI video with H3 Max Turbo (default: renders in seconds, 5-15 s), Grok Imagine, Seedance, Veo, or Kling. Every account gets its first H3 Max Turbo clip at 5 s / 480p free; after that it costs credits like any other preset. Users can name a model family naturally: H3, Hailuo or MiniMax map to H3 Max Turbo, Veo to Veo 3.1 Fast, Kling to Kling 2.5 Turbo, Grok to Grok Imagine, and Seedance to Seedance 2.0 Mini. Seedance 1.5 Pro was retired by its provider on October 21, 2026; if the user asks for it, say so and suggest Seedance 2.0 Mini rather than switching silently. Never omit model when the user named one. Call list_models or quote_generation first when the user wants to review models and costs before spending credits.

Get the remaining credit balance for this account.

The caller's own recent image and video generations on this account, newest first, including ones made on the website. Use it to find an earlier result to show again, edit or animate, then use its task id with check_generation or its URL with edit_image / generate_video. Free; returns records only and never starts anything.

List available image and video models with their credit cost.

Named looks for generate_image: YouTube thumbnails, book covers, album and podcast cover art, posters, blog covers and product photos, four styles each. Free. Call it when the person wants one of those, show the options (in claude.ai they appear as a picker card), then pass the chosen id as style to generate_image with a prompt that describes only the subject.

Plan a complete product-photo workflow: two image directions from one original product photo, user selection, then a short video. Returns exact account prices, prompts, budget guidance and output checks. Free: never starts a generation. Use before making product ads or product videos.

Exact credit cost of a generate_image, edit_image or generate_video call before making it, with the caller's balance and plan eligibility. Use it whenever price or budget comes up instead of estimating. Free; nothing is reserved or started.

Convert an existing raster image (PNG, JPG or WebP) into an editable SVG vector file by tracing it, for 2 credits. Works best on logos, icons, stickers and flat illustrations; photos turn into many small shapes. Pass the full-resolution URL of an earlier result or any public image. To make an SVG from a description, first generate_image a flat design on a plain background (gpt-image-2.6 renders lettering well), then convert that URL.