- 🎨 Design-focused image model built for brand and marketing work
- 🆕 Latest generation of Recraft's proprietary model family, February 2026
- ✍️ Strong typography rendering for posters, packaging, and signage
- 📐 Native editable SVG vector output for design workflows
- 🏢 Tuned for "design taste": balanced composition and cohesive color
- 💰 Same engine as V4 Pro at lower cost, per Venice
- 🔧 Available in raster and vector variants
- 🌐 Accessible inside Recraft Studio and third-party platforms
Recraft is a London-based startup specializing in generative AI for visual content creation. The company develops text-to-image models and offers Recraft Studio, a web-based workspace for creating and editing images, vectors, and mockups. Recraft has built a reputation for…
Explore 1 more model by Recraft →Recraft V4 is the latest generation of Recraft's proprietary, design-focused image model family, released in February 2026. Built by the London-based startup Recraft, it targets professional graphic design rather than general creative use, emphasizing compositional accuracy, typography, and brand consistency. The Recraft team describes its central idea as "design taste" — making deliberate choices about composition, lighting, and color so outputs look art-directed rather than stock-like.
A defining feature is native vector generation: the SVG variants produce actual editable vector files with clean paths and structured layers. V4 also handles text as a structural part of the composition, fitting it into layouts for posters, packaging, and editorial work. This positions the model for brand and marketing assets where legible typography and reusable vector output matter.
Recraft positions V4 as the successor to its earlier generations, including Recraft V3, the family that introduced direct vector generation; the V4 work is framed around design-led decisions rather than general-purpose creativity.
Recraft V4 is offered in raster and vector forms, with Recraft V4 Pro sitting above it for higher-resolution, print-ready output. Venice notes V4 shares the same engine as the Pro tier at lower cost, fitting faster, iterative workflows where maximum resolution is less critical.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
| Seller | Reputation↓ | Routing | $ / img | Categories | API |
|---|---|---|---|---|---|
| Venice.ai Proxy 0x1f22…18c9 | 100.00 | #2 | $0.025 | image,creative | openai-images |
| ▲ Apex Ant 0x73b4…e736 | 91.01 | #1 | $0.02 | image,media | openai-images |
| D5V1N2 0xd5e7…7be0 | 33.17 | gated | $0.058 | image,creative,design,router,fallback | openai-images |
"Best price" and the seller table are live AntSeed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = on-chain trust (0-100). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on AntSeed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.