Google DeepMind (Gemini) / nano-banana-2
Nano Banana 2 stands out for Gemini image workhorse balancing quality and speed and Strong text rendering and multi-reference consistency. It is best suited to daily image generation and editing and high-volume visual production.
Context
—
Not applicable
Input
$0.45
/ 1M tokens
Output
$2.70
/ 1M tokens
Quality
#74
Elo 1080
Overview
Nano Banana 2 stands out for Gemini image workhorse balancing quality and speed and Strong text rendering and multi-reference consistency. It is best suited to daily image generation and editing and high-volume visual production.
Image output
Can generate or return images through media-generation workflows.
Model maker
Google DeepMind (Gemini)
Called through SeaLink's unified account, balance, and OpenAI-compatible API.
Protocol
Media generation API
Base URL: https://api.sealink.io/v1
Pricing
The final charge follows generated usage and the applicable selector, such as resolution, duration, input type, or provider unit.
API
model
nano-banana-2base_url
https://api.sealink.io/v1Auth
Bearer $SEALINK_API_KEYcurl https://api.sealink.io/v1/images/generations \-H "Authorization: Bearer $SEALINK_API_KEY" \-H "Content-Type: application/json" \-d '{"model": "nano-banana-2","prompt": "A serene lake at sunset, oil painting style","n": 1,"aspect_ratio": "16:9","image_size": "1K"}'
import requestsurl = "https://api.sealink.io/v1/images/generations"headers = {"Authorization": f"Bearer {api_key}"}payload = {"model": "nano-banana-2","prompt": "A serene lake at sunset, oil painting style","n": 1,"aspect_ratio": "16:9","image_size": "1K",}resp = requests.post(url, json=payload, headers=headers)data = resp.json()print(data["data"][0]["url"])
const resp = await fetch("https://api.sealink.io/v1/images/generations", {method: "POST",headers: {"Authorization": `Bearer ${process.env.SEALINK_API_KEY}`,"Content-Type": "application/json",},body: JSON.stringify({model: "nano-banana-2",prompt: "A serene lake at sunset, oil painting style",n: 1,aspect_ratio: "16:9",image_size: "1K",}),});const data = await resp.json();console.log(data.data[0].url);