Skip to content

Imagen 4 Fast

Imagen 4 Fast is Google's throughput-optimized image generation model, the fast tier of Imagen 4, built for high-volume pipelines, real-time applications, and rapid creative iteration where generation speed and cost per image determine whether a workflow is viable.

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


const result = await generateImage({
  model: 'google/imagen-4.0-fast-generate-001',
  prompt: 'A red balloon on a wooden table.'
});
OverviewPlaygroundAboutProvidersThroughputLatencySimilarFAQ

Frequently Asked Questions

  • What is the realistic throughput with Imagen 4.0 Fast on AI Gateway?

    Throughput depends on provider-specific rate limits and concurrent request capacity. AI Gateway supports parallel requests, and the fast tier's lower per-request latency allows more generations per unit of time compared to standard or ultra.

  • Can I generate multiple images concurrently in a batch job?

    Yes. Fire concurrent generateImage requests against AI Gateway. The fast tier's lower latency means batch jobs complete faster, and AI Gateway handles retries and failover automatically for reliability under load.

  • What is the cost difference between fast, standard, and ultra tiers?

    Per-image costs appear in the Specs table above. The fast tier is priced below standard, which is priced below ultra. For large-volume workloads, the cost differential compounds significantly. Choose the fast tier if its quality meets your requirements.

  • Does Imagen 4.0 Fast accept image inputs for editing?

    Imagen 4.0 Fast is a text-to-image generation model. For image editing or inpainting workflows, review the AI Gateway model catalog for models that explicitly support image-to-image operations.

  • Do I need a Google Cloud account to use this model?

    No. AI Gateway manages all provider credentials. Authenticate using a Vercel API key or OIDC token.

  • Can I test the fast tier in the playground to compare it against standard or ultra before committing?

    Yes. Visit https://ai-sdk.dev/playground/vertex:imagen-4.0-fast-generate-001 to generate images from any Imagen 4 tier side-by-side without writing integration code. This is the recommended way to evaluate whether the fast tier's output meets your quality bar before committing.

  • Is the fast tier appropriate for production deployments?

    Yes. The fast tier is designed for production throughput, not just prototyping. AI Gateway adds observability, retries, and failover that further support reliable production operation.

  • What happens if I need higher quality for some images in an otherwise fast-tier pipeline?

    AI Gateway's unified API makes it straightforward to route specific requests to a different model tier. Use google/imagen-4.0-generate-001 or google/imagen-4.0-ultra-generate-001 for requests that require higher fidelity, with no infrastructure change required.