Docs
Media Generation
Generate images and videos, remove captions and watermarks.
generate_image
Generate an AI image from a text prompt. Available on every plan. Costs about 1 studio credit per image (GPT Image 2.5 is 0.35, Nano Banana Pro is 1.68); fast=true costs 3 credits.
"Generate a fast image of an astronaut riding a horse on Mars"
| Parameter | Type | Default | Description |
|---|---|---|---|
| prompt | string | required | Description of the image to generate |
| model | string | nano-banana-2 | Model: nano-banana-2 (default, 1), nano-banana-pro (1.68, supports up to 8 reference images), seedream-4.5-edit (1, requires reference_image_url), seedream-5.0-lite (1, optional reference), gpt-image-2.5 (0.35, cheapest). Credits are per image at 1K, and Nano Banana Pro is 2 at 2K and 4K; fast=true is 3 credits (6 on Nano Banana Pro), minimum 3. |
| aspect_ratio | string | 16:9 | Aspect ratio (e.g. 16:9, 9:16, 1:1) |
| reference_image_url | string | null | Optional reference image URL |
| reference_image_urls | array | null | Optional list of reference image URLs (up to 8 on nano-banana-pro; also multi-ref on nano-banana-2, seedream-5.0-lite, gpt-image-2.5). Takes precedence over reference_image_url. |
| fast | boolean | false | Fast mode — bypasses the standard ladder for sub-30s outputs. Costs 3 credits per image, 6 on Nano Banana Pro. Defaults to false. |
Fast mode: set fast=true to bypass the standard provider ladder and route the request through a low-latency lane. Costs 3 credits per image, 6 on Nano Banana Pro. Same models, same prompt; sub-30s outputs in the typical case. Reference images still work.
Generate a thumbnail image of a mysterious dark forest with glowing eyes, 16:9 aspect ratio
generate_video
Generate an AI video from a text prompt. Available on every plan. Cost depends on model, resolution and duration, from about 2.5 credits for a short Grok clip up to several hundred for 4K Seedance. get_credit_balance shows what is left.
"Make a 10-second Grok video of waves crashing on a beach, 16:9"
| Parameter | Type | Default | Description |
|---|---|---|---|
| prompt | string | required | Description of the video to generate |
| model | string | veo3-fast | Model: veo3-fast (default), kling-2.6, grok-text-to-video, grok-image-to-video, seedance-2-mini, seedance-2-fast, seedance-2, seedance-2-5 |
| seconds | string | 4 | Not used. Kept so older clients keep working. |
| size | string | null | Resolution (e.g. 720x1280, 1280x720) |
| duration | string | 5 | Duration in seconds: Kling 5 or 10, Grok 6–30, Seedance 4–15 (1–30 on seedance-2-5) |
| sound | boolean | false | Include audio (Kling and Seedance; free on seedance-2-5) |
| aspect_ratio | string | 9:16 | Aspect ratio (e.g. 9:16, 16:9) |
| input_reference_url | string | null | Reference image URL |
| resolution | string | null | Output resolution: veo3 720p/1080p/4k; grok 480p/720p/1080p; seedance 480p/720p (plus 1080p/4k on seedance-2; seedance-2-5 is 480p/720p only) |
Generate a vertical video of a cat walking through a neon-lit city at night
get_media_job_status
Check the status of a media generation job. Pass the job ID returned by generate_image, generate_video, or generate_tts; returns the job state and, when finished, the hosted result URL.
| Parameter | Type | Default | Description |
|---|---|---|---|
| job_id | string | required | Job ID returned by generate_image, generate_video, or generate_tts |
No example for this one.
get_credit_balance
Check what the user has left to spend. Returns studio credits (spent by image, video, thumbnail and caption-remover generations) with the next monthly reset, plus both voice character pools (ElevenLabs/MiniMax, and Stealth). Free.
"Do I have enough credits for a 10-second Seedance video?"
How many Algrow credits do I have left?
list_generations
The user's own AI Studio history, newest first. Images or videos made in the web Studio, the REST API or these MCP tools, with prompt, model, status, result URLs and timestamps. Images include thumbnails. Paged with limit + offset. Free.
"Find the fox image I made yesterday and give me its link"
| Parameter | Type | Default | Description |
|---|---|---|---|
| kind | string | image | image (default; thumbnails included) or video |
| limit | integer | 20 | How many to return (1–100). Default 20. |
| offset | integer | 0 | Skip this many (for paging). Default 0. |
Show me the last videos I generated
remove_captions
Remove captions or watermarks from a video. Costs 12 credits per minute (0.2 per second, rounded up). Requires Professional or Ultimate plan.
| Parameter | Type | Default | Description |
|---|---|---|---|
| video_url | string | required | URL of the video to remove captions from |
No example for this one.