AI & Compute

Text-to-image generation powered by FLUX.2 [pro]. Send a prompt, get back a 1024x1024 image as base64 JSON or raw bytes, plus a durable direct URL. No API key or account needed.

Generates screenshots of web pages.

Generates animated screenshots or visual content from web pages or specified sources.

Create video using xAI Imagine model (5s × $0.01/s)

Studio X uncensored NSFW video generation with Wan 2.2 Spicy I2V

Generate a finished, high-resolution AI image from a text brief. For agents that need visual assets: thumbnails, illustrations, product shots, concept art, game assets, hero images, marketing graphics. POST JSON {prompt, aspect_ratio} -> 202 with a ticket; poll GET /result/{ticket} (free) for hosted image URLs, ~10s. Content policy: no real-person likenesses, no NSFW, no trademarks.

Generate a short video clip from a text prompt at a flat price per clip: a four-second 720p clip returned inline as base64 MP4, with the duration and resolution locked so the price never moves. Use it when an agent needs motion rather than a still, and needs to know the cost before it calls.

Returns the list of available style keywords (anime, watercolor, cyberpunk, 3d_render, etc.) for /api/image/generate — check it before submitting a paid generation request.

Got an idea? Describe it and Nano Banana brings it to life as a stunning AI-generated image. From realistic portraits to abstract art, any style, any concept.

Generates a 1024x1024 JPEG from a text prompt with FLUX.1 [schnell] in about 2 seconds. Returns a hosted image URL valid for 24 hours that you can hand straight to the next tool; add inline=true to also get the base64. Choose 1-8 diffusion steps (default 4). You are only charged if the image is delivered. No API key, no account.

Returns a generated image url with width, height, and aspect_ratio from a text prompt via Flux — use it for on-demand thumbnails, content art, or product mockups.

Generates a QR code for provided text as SVG markup or a base64 PNG data URI.

Generate a cohesive color palette + CSS variables from a hex seed or brand word. Pay-per-call in USDC.

Generate paste-ready Open Graph + Twitter meta tags for a URL. Provide title/description/image or let it auto-fill from the page. Pay-per-call in USDC.

Automates real Chromium instances in sandbox mode to render dynamic JavaScript pages, returning page HTML or base64 screenshots.

Extracts I-frames and periodic visual keyframes from video streams for computer vision analysis and thumbnail generation.

Create image using GPT-Image-1 AI model

Create video using Sora 2 AI model

Create video using Veo AI model

Generate robots.txt, sitemap.xml, or llms.txt from a domain + paths spec. ?type=robots|sitemap|llms. Pay-per-call in USDC.

Start a premium AI image job using FLUX Kontext Max, background removal, and a 4x upscale. The paid response returns HTTP 202 with a job_id and a free status_url to poll until the transparent high-resolution image succeeds or fails, preventing long generation from being lost to an HTTP proxy timeout.

Translate a passage into a target language. Meaning preserved, no commentary, no transliteration notes.

OCR an image via Google Gemini (sends content to a third party)

Translate up to 2,000 characters into a target language (an ISO 639-1 code or a language name), with the source language detected. Formatting, names, numbers, URLs, and code are preserved. Returns the translation and the detected source. Synchronous, $0.01, no account needed.