Today's price · per 1M tokens
Input
$0.850
per 1M tokens
Output
$1.25
per 1M tokens
Blended
$0.950
blended $/1M — 3:1 weighted input:output
How this price is scoped: Relace's own price, per 1M tokens, as charged on the OpenRouter endpoint Relace operates for this model (provider "Relace", the only endpoint). Relace's pricing page no longer lists Relace Apply 3; since October 2026 it prices only the open models Relace resells, and it says the same models are available through OpenRouter. Until then that page printed $0.80 input / $1.20 output, and Relace's OpenRouter endpoint already charged $0.85 / $1.25 (read 2026-08-07, and again 2026-10-19). Relace publishes no cached-input rate for this model.
Price receipt
We read Relace's own pricing page on and found Relace Apply 3 — Price history listed with a price on the same row — that read is where the number above comes from. We keep the page text we read; its content hash is f5d0a5eee2.
Overview
Relace's code-merge specialist — a fast-apply model that takes the lazy diff a frontier model emits and merges it back into the existing file at over 10,000 tokens per second, so the expensive model never has to regenerate unchanged code. $0.85/$1.25 per 1M tokens.
Capabilities
struck through = not supportedSpecifications
- Provider
- Relace
- Context window
- 256K tokens
- Modality
- text
- Parameters
- Proprietary
- Open source
- No — proprietary
- Released
- Status
- Current
- Last updated
- Tags
Availability verified: — listed on Relace's own page