WaveSpeedAI Desktop is Available Now!Try it
Explore/Google Models

Google Models

google/veo3.1-fast/video-extend

google

$1.05

veo3.1-fast/video-extend

google/nano-banana-pro/edit
google/nano-banana-pro/edit

google

$0.14

nano-banana-pro/edit

google/veo3.1/video-extend

google

$2.8

veo3.1/video-extend

google/veo3.1/text-to-video

google

$3.2

veo3.1/text-to-video

google/veo3.1-fast/text-to-video

google

$1.2

veo3.1-fast/text-to-video

google/veo3.1-fast/image-to-video

google

$1.2

veo3.1-fast/image-to-video

google/veo3.1/reference-to-video

google

$3.2

veo3.1/reference-to-video

google/nano-banana-pro/edit-ultra
google/nano-banana-pro/edit-ultra

google

$0.15

nano-banana-pro/edit-ultra

google/nano-banana-pro/text-to-image-ultra
google/nano-banana-pro/text-to-image-ultra

google

$0.15

nano-banana-pro/text-to-image-ultra

google/nano-banana-pro/text-to-image
google/nano-banana-pro/text-to-image

google

$0.14

nano-banana-pro/text-to-image

google/nano-banana-pro/text-to-image-multi
google/nano-banana-pro/text-to-image-multi

google

$0.07

nano-banana-pro/text-to-image-multi

google/veo3.1/image-to-video

google

$3.2

veo3.1/image-to-video

google/veo3-fast

google

$1.2

veo3-fast

google/imagen4
google/imagen4

google

$0.038

imagen4

google/veo2/image-to-video

google

$2.2

veo2/image-to-video

google/veo3-fast/image-to-video

google

$1.2

veo3-fast/image-to-video

google/veo3/image-to-video

google

$3.2

veo3/image-to-video

google/imagen4-ultra
google/imagen4-ultra

google

$0.058

imagen4-ultra

google/imagen4-fast
google/imagen4-fast

google

$0.018

imagen4-fast

google/imagen3-fast
google/imagen3-fast

google

$0.018

imagen3-fast

google/imagen3
google/imagen3

google

$0.038

imagen3

google/veo3

google

$3.2

veo3

google/veo2

google

$2.5

veo2

google/nano-banana/edit
google/nano-banana/edit

google

$0.038

nano-banana/edit

google/nano-banana/text-to-image
google/nano-banana/text-to-image

google

$0.038

nano-banana/text-to-image

google/gemini-2.5-flash-image-preview/edit
google/gemini-2.5-flash-image-preview/edit

google

$0.038

gemini-2.5-flash-image-preview/edit

google/gemini-2.5-flash-image-preview/text-to-image
google/gemini-2.5-flash-image-preview/text-to-image

google

$0.038

gemini-2.5-flash-image-preview/text-to-image

google/gemini-2.5-flash-image/edit
google/gemini-2.5-flash-image/edit

google

$0.038

gemini-2.5-flash-image/edit

google/gemini-2.5-flash-image/text-to-image
google/gemini-2.5-flash-image/text-to-image

google

$0.038

gemini-2.5-flash-image/text-to-image

google/nano-banana/effects
google/nano-banana/effects

google

$0.038

nano-banana/effects

Google Cloud's Vertex AI platform offers a comprehensive suite of state-of-the-art AI models for image and video generation. These models represent the cutting edge of generative AI technology, combining high performance with enterprise-grade reliability.

Nano Banana Pro is here!!!

🧩 Veo 3.1 — Video Extend (Continue an existing Veo video)

Google’s Video Extend lets you extend a previously Veo-generated video into a longer, continuous clip—preserving motion style, framing, lighting, and synchronized audio for seamless story continuation.

  1. Veo 3.1 Video Extend — Extend an existing Veo video with cinematic continuity (scene, motion, and audio) for “what happens next” storytelling.
  2. Veo 3.1 Fast Video Extend — High-speed, cost-efficient extend workflow for rapid iteration, previews, and multi-branch continuations.

💡 Both endpoints require a Veo-generated input video and return a single merged result containing the original clip plus the extension.

🎬 Veo Series — Text & Image to Video

Google’s Veo family brings cinematic storytelling to AI generation, combining realistic motion, synchronized audio, and true-to-life lighting.

  1. Veo 3.1 — Generates cinematic motion with native dialogue, spatial sound, and realistic scene continuity.
  2. Veo 3.1 Fast — 30% faster and 62.5% cheaper than the base model, while preserving high visual fidelity.
  3. Veo 3.1 I2V — Turns a still image into smooth, lifelike motion with natural ambient audio.
  4. Veo 3.1 Fast l2V — High-performance version for rapid testing, previews, and content iteration.
  5. Veo 3.1 R2V — Transforms a single reference video into a new, high-fidelity scene while preserving motion style, framing, and cinematic tone.
  6. Veo 3 — Flagship text-to-video model from DeepMind, supporting native dialogue, ambient sound, and realistic motion.
  7. Veo 3 Fast — 30% faster and 62.5% cheaper; optimized for short-form and social content.
  8. Veo 3 I2V — Converts still images into smooth, lifelike motion with synchronized audio.
  9. Veo 3 Fast I2V — High-speed, cost-efficient version for rapid iteration.
  10. Veo 2 I2V — Legacy generation model with nostalgic or stylized motion.
  11. Veo 3.1 - Generates cinematic motion with native dialogue, spatial sound, and realistic scene continuity.
  12. Veo 3.1 Fast - 30% faster and 62.5% cheaper than the base model, while preserving high visual fidelity.
  13. Veo 3.1 I2V - Turns a still image into smooth, lifelike motion with natural ambient audio.
  14. Veo 3.1 Fast l2V - High-performance version for rapid testing, previews, and content iteration.

💡 All Veo models include synchronized audio (speech, ambiance, and music) and support up to 1080p output.

🖼️ Imagen Series — Text & Image Generation

The Imagen series excels in realism, lighting control, and precise text rendering, making it ideal for photography, design, and illustration.

  1. Imagen 4 Ultra — Premium 2K photorealistic generation with advanced lighting and texture fidelity.
  2. Imagen 4 Fast — Streamlined version offering strong quality with faster, lower-cost output.
  3. Imagen 4 — Standard high-fidelity generation with excellent text handling and composition accuracy.
  4. Imagen 3 Fast — Lightweight, fast model ideal for lifestyle or blog-style imagery.
  5. Imagen 3 — Balanced base model for portraits, scenery, and artistic concept generation.

🪄 Nano-Banana & Gemini — Lightweight Creative Tools

For quick everyday creation, Google’s lightweight models deliver expressive results with speed and efficiency.

  1. Nano-Banana / Text-to-Image — Create quick, expressive visuals from text prompts.
  2. Nano-Banana / Edit — Modify or enhance existing images with natural language instructions.
  3. Gemini 2.5 Flash Text-to-Image — Generate soft, detailed visuals through Google’s Gemini integration.
  4. Gemini 2.5 Flash Edit — Smart, context-aware photo editing with lighting consistency.
  5. Nano-Banana Pro / Text to Image — Produce sharper, higher-fidelity images with improved prompt control for production use.
  6. Nano-Banana Pro / Edit — Apply precise, region-aware edits that preserve identity, lighting, and overall composition.
  7. Nano-Banana Pro / Ultra — Generate ultra-detailed, high-resolution visuals for hero shots, key art, and premium campaigns.
  8. Nano-Banana Pro / Multi — Combine multiple reference images or styles to build complex, consistent characters and scenes.

📝 Notes

Please ensure your prompts comply with Google’s Safety Guidelines.

If an error occurs, review your prompt for restricted content, adjust it, and try again.