ScaleDown: Summarize-1

ScaleDown: Summarize-1

byScaleDown

Summarize-1 is a language model from ScaleDown released on Oct 20, 2026. It reads text and writes text, with a 1M token context window and up to 1K tokens per reply.

Show more

It costs $0.05 per million input tokens and $0 per million output tokens.

Modalities
In / out price
$0.05 / $0 per 1M
Context
1M
Max output
1K
Released
Oct 20, 2026
Knowledge cutoff
n/a
  • Tool calling
  • Structured output
  • Reasoning
  • Prompt caching
  • Open weights
  • Free to use

Summarize-1 pricing

USD, as listed on Oct 22, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.

Input$0.05 / 1M tokens
Output$0 / 1M tokens

What Summarize-1 costs per month

Pick a workload close to yours or type your own volumes.

Summarize-1 per month
$3.75
Without caching
$3.75
Per request
$0.0001

Alternatives to Summarize-1

Models that take the same inputs, closest in price, cheaper ones first.

More from ScaleDown

  • Reads text.

    by scaledownOct 20, 2026$0.05/M input tokens$0/M output tokens

  • Reads text, images and files.

    by scaledownOct 13, 2026$0.05/M input tokens$0/M output tokens

  • Reads text, images and files.

    by scaledownOct 13, 2026$0.05/M input tokens$0/M output tokens

All ScaleDown models

Summarize-1 questions

How much does the Summarize-1 API cost?

$0.05 per million input tokens and $0 per million output tokens. The estimator on this page turns that into a monthly bill for your own workload.

What is the context window of Summarize-1?

1,000,000 tokens of input, and it can write up to 1,000 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.

Does Summarize-1 support tool calling?

Not through the standard tools parameter. For an agent that calls your APIs, pick a model from the alternatives below that does.

Is Summarize-1 open source?

No. ScaleDown serves it through an API only, so you cannot download the weights or host it yourself.

When was Summarize-1 released?

Oct 20, 2026.

Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 22, 2026. The summary is written from these facts.