Home / Models / Scaledown / Summarize
SScaledown

Summarize pricing

$0.04 per 1M input tokens and $0 per 1M output tokens. In real work that is <0.01¢ per chat answer and 0.05¢ to summarize a 20-page PDF.

Input / 1M$0.04
Output / 1M$0
Cached input / 1Mn/a
Chat answer<0.01¢
Context1M
Quality-

What Summarize costs per task

Token counts estimated from a measured model of the same lab (Qwen3.8 Flash), rescaled by tokenizer. Reasoning tokens are billed as output.

TaskCostTokens usedPrice rankBasis
Answer a chat question
<0.01¢$0.0035 / 1,000
88 in · 689 out · 909 reasoning1 of 336estimated
Reply to a customer email
<0.01¢$0.01 / 1,000
326 in · 98 out · 587 reasoning1 of 336estimated
Write a 1,500-word blog post
≥<0.01¢$0.0042 / 1,000
104 in · 0 out · 16,000 reasoning1 of 336estimated
Write 10 product descriptions
≥<0.01¢$0.01 / 1,000
345 in · 0 out · 16,000 reasoning1 of 336estimated
Translate 1,000 words
<0.01¢$0.06 / 1,000
1,386 in · 1,166 out · 136 reasoning1 of 336estimated
Proofread one page (500 words)
<0.01¢$0.03 / 1,000
777 in · 671 out · 1,159 reasoning1 of 336estimated
Summarize a 20-page PDF
0.05¢$0.52 / 1,000
13,119 in · 501 out · 2,141 reasoning6 of 336estimated
Extract data from an invoice
<0.01¢$0.02 / 1,000
501 in · 561 out · 1,617 reasoning1 of 336estimated
Analyze a 200-row spreadsheet
≥0.03¢$0.25 / 1,000
6,357 in · 0 out · 16,000 reasoning1 of 336estimated
Answer from 5 retrieved documents (RAG)
0.01¢$0.15 / 1,000
3,751 in · 974 out · 1,912 reasoning2 of 336estimated
Classify 100 support tickets
<0.01¢$0.06 / 1,000
1,463 in · 534 out · 7,879 reasoning1 of 336estimated
Review 500 lines of code
≥0.02¢$0.20 / 1,000
4,874 in · 0 out · 16,000 reasoning1 of 336estimated
Write a SQL query
<0.01¢$0.0071 / 1,000
177 in · 405 out · 2,225 reasoning1 of 336estimated
Run a 50-step coding agent
9.0¢$90.40 / 1,000
2,259,875 in · 15,150 out · 80,850 reasoning45 of 336modeled

Price at every provider

List prices per 1M tokens (input / output) at each host serving Summarize through OpenRouter today. Hosts can differ in quantization, context and speed.

ProviderInput / outputCached inputContextUptime
S
ScaleDownunknown
$0.04 / $0-1M100%

Price history

First seen in our price history on Oct 16, 2026 at $0.04 input / $0 output. The list price has not changed since.

$0$0.011$0.023$0.035$0.046Oct 2026Oct 2026Oct 2026Oct 2026Oct 2026
Output per 1MInput per 1M

FAQ

How much does Summarize cost?

Summarize costs $0.04 per 1 million input tokens and $0 per 1 million output tokens (list price on Oct 18, 2026). In practice one chat answer costs about <0.01¢ and summarizing a 20-page PDF about 0.05¢.

Where is Summarize cheapest?

Among 1 providers we track, the lowest list price today is at ScaleDown: $0.04 input and $0 output per 1M tokens.

Is the Summarize cost per task measured or estimated?

Estimated: Summarize was not run directly. Tokens come from Qwen3.8 Flash and are rescaled by the tokenizer of Scaledown. Real usage can differ.