Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the...
With CoreAI, you can start chatting with ScaleDown: Extract instantly — no separate subscription needed. CoreAI lets you chat with ScaleDown: Extract alongside 300+ other AI models from Scaledown and other providers like OpenAI, Anthropic, Google, Meta, and more.
ScaleDown: Extract holds the #123 spot for context size out of 445 chat models in the CoreAI catalog — 1M tokens, roughly 750,000 words or 1,500 pages of text in a single conversation. On price, it is the #19 cheapest of 156 budget-tier models by input cost. Released 2026-10-13, it is one of the 4 newest additions to the catalog. It accepts image input alongside text.
Every model in this table is available on CoreAI — open the web app and run the same prompt through ScaleDown: Extract and ScaleDown: Summarize side by side to judge with your own eyes.
A typical question (about 1,000 tokens in, 500 out) runs $0.00004 on ScaleDown: Extract's raw per-token rates; a heavy session with a 50K-token document costs about $0.002. On CoreAI you don't juggle these numbers — one subscription covers ScaleDown: Extract and 300+ other models under a plan usage limit, with no API keys. See plans.
ScaleDown: Extract handles 1M tokens of context — roughly 750,000 words, or about 1,500 pages of text in one conversation.
ScaleDown: Extract's underlying rates are $0.04 per 1M input tokens and $0 per 1M output tokens. On CoreAI it is included in one subscription alongside 300+ models, so there is no per-token billing to manage.
Yes — ScaleDown: Extract accepts image input, so you can attach screenshots, photos or diagrams and ask questions about them.
No — ScaleDown: Extract answers directly without an extended reasoning phase, which usually means faster responses.
Open the CoreAI web app or the iOS/Android app, pick ScaleDown: Extract in the model selector, and chat — no API key, no per-token billing. One subscription covers ScaleDown: Extract and 300+ other models.
The closest alternatives on CoreAI are ScaleDown: Summarize, NVIDIA: Switchyard, DeepSeek: DeepSeek V4 Flash Latest — similar tier and capability. The fastest way to choose is running one prompt through them side by side in CoreAI's Compare view.
Chat with ScaleDown: Extract and 300+ other AI models — all in one app.