バリアント · Google / Nano Banana

Nano Banana nano-banana-2 API

A model variant exposed through RunAPI's unified AI API.

Operational · image · Commercial use supported
# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/nano-banana -g
The -g flag installs globally so every project picks it up.
Or paste this prompt to your AI agent:
Install the Nano Banana skill for me:

1. Clone https://github.com/runapi-ai/nano-banana
2. Copy the skills/nano-banana/ directory into your
   user-level skills directory (e.g. ~/.claude/skills/
   for Claude Code, ~/.codex/skills/ for Codex).
3. Verify that SKILL.md is present.
4. Confirm the install path when done.
Switch variant
概要

Nano Banana nano-banana-2 is available through the same RunAPI auth, SDKs, and agent skill workflow.

  • Unified endpoint
  • SDK snippets
  • Agent install path
  • 失敗した生成は課金されません
料金

料金

失敗した生成は課金されません
Text to image
$0.16-$0.36 / image
Output resolution: 1k $0.16
Output resolution: 2k $0.24
Output resolution: 4k $0.36
仕様

仕様

Model ID nano-banana-2
プロバイダー Google
モダリティ image
Task type asynchronous
課金 call
Endpoint /api/v1/nano_banana/text_to_image
Commercial Yes
Status Operational
クイックスタート

Quickstart — nano-banana-2

runapi.ai
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "nano-banana-2",
  "prompt": "Create a motivational poster with the text 'Never Give Up' in bold serif, sunset mountains in the background."
}'
import { NanoBananaClient } from "@runapi.ai/nano-banana";

const client = new NanoBananaClient();
const result = await client.textToImage.run({
    model: "nano-banana-2",
    prompt: "Create a motivational poster with the text 'Never Give Up' in bold serif, sunset mountains in the background.",
});
require "runapi/nano_banana"

client = RunApi::NanoBanana::Client.new
result = client.text_to_image.run(
    model: "nano-banana-2",
    prompt: "Create a motivational poster with the text 'Never Give Up' in bold serif, sunset mountains in the background."
)
@runapi.ai/nano-banana v1
仕組み

How to use nano-banana-2

01

Choose endpoint

Pick the endpoint and copy the SDK snippet.

02

Pass model ID

Use this variant ID in the request body.

03

Run task

Submit the request and store the returned task ID.

04

Collect output

Poll or receive the callback when the task finishes.

違い

How nano-banana-2 compares

VS NANO-BANANA

Built on Gemini 3.1 Flash; best multi-character consistency, 4–8s

1K resolution; fast and cheap baseline (Aug 2025)

VS NANO-BANANA-EDIT

Built on Gemini 3.1 Flash; best multi-character consistency, 4–8s

Prompt-driven image editing from an existing image

VS NANO-BANANA-PRO

Built on Gemini 3.1 Flash; best multi-character consistency, 4–8s

Built on Gemini 3 Pro; 4K resolution, best text rendering, 10–20s

ユースケース

Where to use this variant

Image generation

Create visual assets from text prompts.

Editing

Transform existing images with prompt guidance.

Batch creative work

Use SDKs for repeatable generation.

FAQ

Frequently asked questions about nano-banana-2

How do I select nano-banana-2?

Pass the model ID shown in the quickstart.

Is pricing usage-based?

Yes. Pricing is metered per call or unit.

今すぐ開始

Start with Nano Banana today.