Spider read replicate.com in 108 ms without a browser and returned 575 lines of clean markdown, including sections like "Run models" and "Fine-tune models with your own data".
Seedance 2.5 is coming soon ## Run AI with an API. # Run and fine-tune models. Deploy custom models. All with one line of code. Get started for free ``` `import Replicate from ` ``` "replicate" ``` `;` ``` ``` `const replicate = new Replicate({` ``` ``` ` auth: process.env.REPLICATE_API_TOKEN` ``` ``` `})` ``` ``` `const model = ` ``` ``` `` ``` ``` `const input = {` ``` ``` ` prompt: ` ``` ``` `` ``` ``` `};` ``` ``` `const [output] = await replicate.run(model, { input });` ``` ``` `console.log(output);` ``` A poolside patio at sunset with vintage lounge chairs. black-forest-labs/flux-2-pro A soft armchair shaped like a peeled banana. google/nano-banana-pro A woman relaxing in a french bookstore. bytedance/seedream-4 A futuristic robot looking into the distance. black-forest-labs/flux-pro An abstract painting of a sunrise. black-forest-labs/flux-pro With Replicate you can Generate imagesGenerate speechGenerate musicRestore imagesGenerate videos from imagesCaption ImagesLarge Language Models (LLMs) google / nano-banana-pro Google's state of the art image generation and editing model 🍌🍌 33.6M runs Official google / nano-banana-2 Google's fast image generation model with conversational editing, multi-image fusion, and character consistency 16.2M runs Official openai / gpt-image-2 OpenAI's state-of-the-art image generation model. Create and edit images from text with strong instruction following, sharp text rendering, and detailed editing. 19M runs Official bytedance / seedream-4.5 Seedream 4.5: Upgraded Bytedance image model with stronger spatial understanding and world knowledge 35.3M runs Official black-forest-labs / flux-2-flex Max-quality image generation and editing with support for ten reference images 455K runs Official openai / gpt-image-1.5 OpenAI's latest image generation model with better instruction following and adherence to prompts 14.9M runs Official bytedance / seedream-5-lite Seedream 5.0 lite: image generation with built-in reasoning, example-based editing, and deep domain knowledge 3.2M runs Official google / imagen-4-ultra Use this ultra version of Imagen 4 when quality matters more than speed and cost 1.8M runs OfficialYou can get started with any model with just one line of code. But as you do more complex things, you can fine-tune models or deploy your own custom code.### Run modelsOur community has already published thousands of models that are ready to use in production. You can run these with one line of code.` "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic",`### Fine-tune models with your own dataYou can improve models with your own data to create new models that are better suited to specific tasks.Image models like SDXL can generate images of a particular person, object, or style.`training = replicate.trainings.create(`` destination="mattrothenberg/drone-art"`` version="ostris/flux-dev-lora-trainer:e440909d3512c31646ee2e0c7d6f6f4923224863a6a10c494606e79fb5844497",`https://example.com/images.zip
↓
Code · Fields · Cost ·
Run it keyless, no account
The same call, in code.
The capture above came back as markdown. These examples add a key, so you get browser rendering, proxies, and concurrency on replicate.com.
replicate-scraper.ts
import { SpiderBrowser } from "spider-browser";const spider = new SpiderBrowser({ apiKey: process.env.SPIDER_API_KEY!,});await spider.connect();const page = spider.page!;await page.goto("https://replicate.com/explore");// No selectors, no schema. Spider reads the page and names the fields.const data = await page.scrape();console.log(data);await spider.close();
Model nameAuthorRuns countDescriptionLicenseHardwareCost per runTags
Spider names these from the page. The capture above came back as markdown; the same
call with return_format: "json" returns them as keys.
What replicate.com costs to scrape.
The capture above cost $0.000556 to fetch. Pricing is $1 per GB of pre-transformation bandwidth plus $0.001 per CPU minute, so a page like this one lands at a fraction of a cent. Failed requests are billed at $0.
You already have the call. A key raises the rate limit and turns on browser rendering,
proxies, and concurrency. Balance never expires, and top-ups go through secure checkout.