- 🎨 Design-focused image model emphasizing typography and brand layouts
- 🆕 V4 rebuilt around "design taste" composition and material realism
- 🔧 Generates editable vector output directly from prompts
- 📝 Integrated text rendering where typography interacts with the scene
- 🏢 Built for brand, marketing, and print-ready design work
- 📏 Pro tier targets high-resolution, high-fidelity output
- 🖼️ Available within Recraft Studio alongside other models
- 💬 Released February 2026 by London-based Recraft
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 Pro is the high-resolution tier of London-based Recraft's V4 image family, released in February 2026 and tuned for professional design and branding work. It shares the same engine as the standard Recraft V4 — including its "design taste," prompt accuracy, and creative capabilities — but targets higher resolution for print-ready assets, large-format work, and detailed compositions. Recraft describes Pro delivering finer detail, cleaner geometry, and improved realism for high-fidelity applications.
The V4 generation is positioned by Recraft as a rebuild focused on what it calls "design taste": deliberate decisions about composition, lighting, color relationships, and material realism. V4 emphasizes integrated text rendering, where typography interacts with the scene rather than sitting on top as a decorative layer.
A defining feature across the family is native vector generation: Recraft produces editable vector files with structured layers and clean paths directly from a prompt, without a separate tracing or conversion step.
V4 Pro supports multiple aspect ratios and longer prompts, making it suited to posters, packaging, logos, icons, and design-system components. It is available within Recraft Studio alongside Recraft's other text-to-image and editing models.
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 | $0.145 | image,creative | openai-images |
| ▲ Apex Ant 0x73b4…e736 | 91.01 | #1 | $0.12 | image,media | openai-images |
| D5V1N2 0xd5e7…7be0 | 33.17 | gated | $0.336 | 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.