ScaleDown · language model
Extract: pricing, context and benchmarks
Extract is ScaleDown's model released on October 13, 2026. It costs $0.04 per million input tokens and $0 per million output tokens, with a 1M-token context window. No independent score has been published for it so far.
What you need to know about Extract
ScaleDown put Extract online on October 13, 2026. It accepts text, images, and files as input and produces text. Its context window reaches 1,000,000 tokens, larger than 77 % of the models in the registry, and it can write up to 900,000 tokens in one go.
It is a recent model: real-world feedback and independent scores are still scarce.
Extract pricing
On OpenRouter, Extract costs $0.04 per million input tokens and $0 per million output tokens. Counting three tokens read for every token written, its average price is $0.03 per million, more expensive than 1 % of paid models (25.4 times cheaper than the median of $0.76).
A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.0001. At 1,000 tasks a day, budget $2 a month. The price calculator redoes this with your own volumes.
Performance and benchmarks
Epoch AI does not yet publish a capabilities index for Extract. We therefore show no made-up performance rating: only price, context and features count towards its score.
Features, privacy and local use
- It does not support tool calling: it is not suited to driving an AI agent that has to act.
Its weights are not published: it can only be used through the ScaleDown API or a broker such as OpenRouter, which means sending your data off your machines.
Other ScaleDown models
| Model | Released | Avg. price | ECI |
|---|---|---|---|
| Summarize | Oct 13, 2026 | $0.03 | — |
Verdict
Computed score: 70/100, from public data (performance, price, context, features).
Strengths
- Low price: cheaper than 99 % of paid models.
- Very large context (1M tokens): long documents or a whole codebase fit in one request.
Limitations
- No tool calling: unusable as an agent's brain.
- No independent score published: performance cannot be verified.
Avoid if…
- your data must not leave your servers;
- you are building an agent that must call tools.
Alternatives
- Qwen3.7 Flash$0.06
- Dots3-Note Previewfree
- Lyria 3 Pro Previewfree
- Lyria 3 Clip Previewfree
- Ling 3.0 Flash$0.03
- Qwen3.5-Flash$0.11
Comparisons and tools
Learn more
Frequently asked questions
How much does Extract cost?
$0.04 per million input tokens and $0 per million output tokens on OpenRouter (checked October 25, 2026). A task with 2,000 tokens read and 500 written costs $0.0001.
How big is Extract's context window?
1,000,000 tokens, roughly 750,000 words, with a maximum of 900,000 output tokens.
Can Extract run locally?
No, ScaleDown does not publish its weights: it is API-only.
Is Extract suitable for an AI agent?
No: without tool calling it cannot act, only answer.
What are the alternatives to Extract?
The closest models on price and performance are Qwen3.7 Flash, Dots3-Note Preview, and Lyria 3 Pro Preview.
Related articles
- Mistral AI: models, pricing and agentsOctober 25, 2026
- LLM benchmarks: how to read model rankingsOctober 24, 2026
- Running a local LLM: hardware, software, and limitationsOctober 24, 2026
- Open-source or closed models for your AI agents?October 5, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score