← All models
Flash — fastest and cheapest, lighter reasoningCommercial API
Extract Pricing
ScaleDown · scaledown-extract
Input / 1M tokens
$0.040
Output / 1M tokens
$0.00
Context window
1M tokens
≈ 1,333 pages of text
Max output
900k tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0
1,000 requests / month$0.048/mo10,000 requests / month$0.48/mo100,000 requests / month$4.80/moEstimate your own workloadOpens the calculator with Extract preloaded — adjust volume and token counts there.
Price history
Only one price point recorded so far.
The staircase chart appears once a price change is detected.
What it excels at
Supports 1M-token contexts and 900k output at $0.04/M input with zero output cost, enabling high-volume extraction from long documents.
The business tradeoff
Zero output pricing and unknown provider suggest limited reasoning depth, minimal ecosystem integration, and potential variance in reliability.
Head-to-head
Vendor list rates, as of Oct 13, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.