LogoreAPI
  • Models
  • Blog
  • API Docs
  • API Updates
LogoreAPI

reAPI is the AI API aggregator with sub-second failover, zero request logging, and one OpenAI-compatible endpoint for every top model.

GitHubX (Twitter)YouTube
Built withLogo of reAPIreAPI
Featured on There's An AI For ThatFeatured on Findly.toolsFazier badgeDang.ai
ai tools code.market
Featured on Twelve Tools
Image
  • GPT Image 2
  • Gemini 3 Pro Image
  • Gemini 3.1 Flash Image
  • Gemini 2.5 Flash Image
  • Seedream 5.0 Lite
Video
  • Seedance 2.0
  • Happy Horse 1.0
  • Vidu Q3
  • Grok Imagine 1.0
  • VEO 3.1
Tools
  • Enhance Video 1.0
Resources
  • Blog
  • About
  • Contact
  • API Updates
  • Cookie Policy
  • Privacy Policy
  • Terms of Service
Β·Β·Β·Β·Β·Β·Β·
Β© 2026 reAPI. All Rights Reserved.

API Updates

Latest model launches, capability upgrades, and routing changes across the reAPI platform

Nano Banana Pro & Nano Banana 2

2026/5/7

We're shipping the full Nano Banana family on reAPI today β€” Google's image generation lineup, fully OpenAI-compatible and ready to wire into your stack: Nano Banana Pro, Nano Banana 2, and the original Nano Banana. One base URL, one API key, three model IDs.

New Models

Nano Banana Pro

  • Model ID: gemini-3-pro-image-preview
  • Provider: Google
  • Best For: Studio-grade output with sub-pixel text rendering, 1K / 2K / 4K resolution tiers, brand-safe production work
  • Highlights: Up to 14 reference images, 14 aspect ratios (including extreme 1:8 / 8:1 / 1:4 / 4:1), official-channel routing for compliance-sensitive workloads

Nano Banana 2

  • Model ID: gemini-3-1-flash-image-preview
  • Provider: Google
  • Best For: High-throughput generation with grounded prompts, fast iteration on creative concepts
  • Highlights: Optional Google Search and Google Image Search grounding for fact-aware prompts, n=1-4 per request, 0.5K – 4K resolution

Nano Banana

  • Model ID: gemini-2-5-flash-image-preview
  • Provider: Google
  • Best For: Fast, cost-efficient image generation at scale
  • Highlights: Up to 14 reference images, OpenAI Chat-Completions-shaped requests, the same auth and billing surface as the rest of reAPI

Endpoint

All three models accept the same POST /api/v1/images/generations request shape. Drop in your reAPI key, point your client at https://reapi.ai/api/v1, and switch the model field to any of the IDs above.