Recraft V3 Edit is the image-to-image counterpart to Recraft's V3 model, built for transforming a supplied source image rather than generating one from scratch. You provide the starting image and a prompt describing the change, and the model reworks the picture while drawing on the same design-oriented engine as the base model. Because it inherits Recraft's full style system, including vector styles and custom brand styles, it excels at restyling existing assets, converting drafts into polished brand-consistent artwork, and producing controlled variations of an image. It fits design teams iterating on visual material and pipelines that adapt one source visual into many styled outputs.
Usage-based pricing, billed per generation, not by token.
| Variant | Price |
|---|---|
| Standard | $0.04 / generation |
Recraft V3 runs on 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Price |
|---|---|---|---|---|
| US | Enterprise | No | $0.04 / generation |
Each route hosting Recraft V3 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.
Call Recraft V3 through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.OPPER_API_KEY,baseURL: "https://api.opper.ai/v3/compat",});const completion = await client.chat.completions.create({model: "fal/recraft-v3-edit",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.