GET models.dev HTTP 200136 ms86.6 KB$0.002347 captured Aug 7, 2026
models.dev, as data
One API turns any models.dev page into markdown, structured JSON, its link graph or a screenshot, and crawls the whole site the same way. The panel shows the real response we captured.
- Render mode
- Plain HTTP, no browser needed
- Response
- HTTP 200 in 136 ms
- Page size
- 86.6 KB of markdown, 594 lines
- Fields
- Business Name, Address, Phone, Category and 2 more
- Captured
- Aug 7, 2026
Free balance on signup, no card. This models.dev page cost $0.002347 to fetch.
Llama 3.1 Nemotron 70B Instructnvidia/llama-3.1-nemotron-70b-instructGPT-4.1 miniopenai/gpt-4.1-miniGPT-4.1 nanoopenai/gpt-4.1-nanoLlama 3.1 Nemotron Ultra 253Bnvidia/llama-3.1-nemotron-ultra-253bLlama 3.3 Nemotron Super 49B v1nvidia/llama-3.3-nemotron-super-49b-v1Llama 4 Maverick 17B Instructmeta/llama-4-maverick-17b-instructLlama 4 Scout 17B Instructmeta/llama-4-scout-17b-instructQwen3 235B-A22Balibaba/qwen3-235b-a22bQwen3-Coder 30B-A3B Instructalibaba/qwen3-coder-30b-a3b-instructQwen3-Coder 480B-A35B Instructalibaba/qwen3-coder-480b-a35b-instructQwen-Omni Turboalibaba/qwen-omni-turboMagistral Medium (latest)mistral/magistral-medium-latestCommand Acohere/command-a-03-2025Command R7B Arabiccohere/command-r7b-arabic-02-2025Claude Sonnet 3.7anthropic/claude-3-7-sonnet-20250219Codestral (latest)mistral/codestral-latestDeepSeek-V3deepseek/deepseek-v3Gemini 2.0 Flashgoogle/gemini-2.0-flashGemini 2.0 Flash-Litegoogle/gemini-2.0-flash-litePhi-4-minimicrosoft/phi-4-miniLlama-3.3-70B-Instructmeta/llama-3.3-70b-instructCommand R7Bcohere/command-r7b-12-2024GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20Mistral Large 2.1mistral/mistral-large-2411Qwen2.5-Coder-0.5Balibaba/qwen2.5-coder-0.5bPixtral Large (latest)mistral/pixtral-large-latestAya Expanse 32Bcohere/c4ai-aya-expanse-32bAya Expanse 8Bcohere/c4ai-aya-expanse-8bClaude Haiku 3.5anthropic/claude-3-5-haiku-20241022Claude Sonnet 3.5 v2anthropic/claude-3-5-sonnet-20241022Ministral 8B Instructmistral/ministral-8b-instruct-2410 What Spider does on models.dev
Same key, five endpoints. The numbers under a cell were measured on this page.
Page to markdown
Clean text for RAG and LLM context, boilerplate removed. The lane that runs without a key.
136 ms · $0.002347Page to JSON
Spider reads the page and names the fields. Pass your own schema when you need exact keys.
Rendered capture
Real Chromium, full-page PNG. The same call also returns the rendered HTML.
The call behind the panel
This request produced the response above. Paste it with your key and you get the same bytes.
curl -X POST https://api.spider.cloud/scrape \
-H "Authorization: Bearer $SPIDER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"url": "https://models.dev/", "return_format": "markdown"}' from spider import Spider
app = Spider()
params = {"return_format": "markdown"}
page = app.scrape_url("https://models.dev/", params=params)
print(page[0]["content"]) import { Spider } from "@spider-cloud/spider-client";
const app = new Spider();
const [page] = await app.scrapeUrl("https://models.dev/", {
return_format: "markdown",
});
console.log(page.content); What models.dev costs
Multiplied from the measured 86.6 KB page. Estimates round to the cent.
1 GB of transfer costs $1, plus $0.001 per CPU minute, and failed requests cost $0. Crawling daily? The Unlimited plan is a flat monthly rate.
Point this at the rest of models.dev.
The capture above took 136 ms and cost $0.002347. The same call takes any URL on models.dev.