Skip to content

Recraft V2

Recraft V2 is Recraft's foundational image generation model. It delivers photorealistic output, accurate text rendering, and complex prompt following for production design workflows.

Image Gen
index.ts
import { experimental_generateImage as generateImage } from 'ai';


const result = await generateImage({
  model: 'recraft/recraft-v2',
  prompt: 'A red balloon on a wooden table.'
});
OverviewPlaygroundAboutProvidersThroughputLatencySimilarFAQ

Frequently Asked Questions

  • What are the core strengths of Recraft V2?

    Photorealistic image generation, accurate text rendering, and complex prompt following. These three capabilities form the foundation of the Recraft model family.

  • How does Recraft V2 handle text in generated images?

    It renders legible, correctly spelled text within generated scenes. Use it for signage, labels, product mockups, and other cases where on-image text must be accurate.

  • Should I use Recraft V2 or upgrade to a newer Recraft model?

    Stick with V2 if your integration meets your requirements. Upgrade to Recraft V3 or V4 if you need improved photorealism, expanded style presets, or higher-resolution output.

  • Is Recraft V2 a multimodal LLM?

    No. Recraft V2 is a dedicated image generation model. It doesn't process conversation history or maintain a context window. Use generateImage from the AI SDK to send requests.

  • How do I use Recraft V2 on AI Gateway?

    Pass recraft/recraft-v2 to generateImage from the AI SDK. AI Gateway routes the request to available providers and handles retries and failover automatically.

  • What does Recraft V2 cost?

    See the pricing section on this page for today's rates. AI Gateway exposes each provider's pricing for Recraft V2.

  • What types of images does Recraft V2 handle well?

    Photorealistic scenes, product imagery, and compositions with readable text. It handles multi-clause prompts that specify subject, composition, and style at once.