A URL in the prompt
Interfaze reads a public URL that you put in the user message, then fills the JSON schema you send. On AnyRouter that call is a normal chat completion. Set the model to interfaze/interfaze-1.
Interfaze documents the same idea on their scraping page. Their own SDK also returns the raw page extract on precontext, from a tool named web_extract. AnyRouter returns an OpenAI chat completion. Read the JSON on choices[0].message.content.
Use a URL you are allowed to fetch. A long page is expensive. Interfaze's published profile example reports 22,451 prompt tokens and 49,971 completion tokens.
Two models, one key
Interfaze 1interfaze/interfaze-1 is the flagship. It takes text, images, audio, files, and video, returns text, and has a 1,000,000-token context. List price on 22 November 2026 is $1.50 per million input tokens and $3.50 per million output tokens.
Interfaze 1.1 Lite is the smaller open-weight model. It takes text, images, audio, and files, returns text, and has a 131,072-token context. List price is $0.85 per million input tokens and $1.50 per million output tokens. The weights are on Hugging Face and run on one 80 GB GPU.
Both routes are bring-your-own-key. Create a key in the Interfaze dashboard, add it under Dashboard, BYOK, Interfaze, and call AnyRouter with an sk-ar-v1- key. Interfaze bills your key. AnyRouter does not charge credits for the hop.
Ask for a title and a summary
The sample asks for the title and a one-sentence summary of Interfaze's own scraping page.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://anyrouter.dev/api/v1",
api_key=os.environ["ANYROUTER_API_KEY"],
)
completion = client.chat.completions.create(
model="interfaze/interfaze-1",
messages=[
{
"role": "user",
"content": "Extract the title and a one-sentence summary from https://interfaze.ai/docs/web/web-scraping",
}
],
response_format={
"type": "json_schema",
"json_schema": {
"name": "page",
"schema": {
"type": "object",
"properties": {
"title": {"type": "string"},
"summary": {"type": "string"},
},
"required": ["title", "summary"],
"additionalProperties": False,
},
},
},
)
print(completion.choices[0].message.content)The same call works from the TypeScript OpenAI SDK and from the Vercel AI SDK. The full tabs, including the AI SDK snippet, are in the scrape guide.
Or call the scrape tool
Interfaze also publishes a hosted MCP server. Connect it from MCP connectors as Interfaze. The server URL is https://api.interfaze.ai/mcp. Paste the same Interfaze API key. Their MCP page lists scraper plus search, OCR, transcription, translation, and forecast.
That connection calls Interfaze directly. It does not go through interfaze/interfaze-1 on the chat API.
Related posts
- Use AnyRouter with the Vercel AI SDKGuidesJuly 19, 2026 · @anyr/ai-sdk-provider wraps the AnyRouter gateway as a standard Vercel AI SDK provider. Call createAnyRouter(), pass a provider/model id, and generateText, streamText, and generateObject work unchanged, switching models is a one-string edit.
- Bring your own keys: every provider behind one APIProductJune 28, 2026 · Connect the provider keys and subscriptions you already pay for, route them through one OpenAI-compatible URL with automatic failover, and, soon, earn credits back by donating idle quota to the shared pool.
- What is AnyRouter? A plain-English guide to AI model routingGuidesAugust 5, 2026 · An AI model router lets you call many LLMs through one API. Here's what AnyRouter is, why it exists, and whether it's useful for your next project.
Pick a plan and start
Go is $2 a month for $4 in credits.
Pro is $10 a month for $20 in credits.
Pro+ is $45 a month for $100 in credits.
Max is $100 a month for $300 in credits.
Create an account, pay on the next screen, then call the model.