Image · Google

Nano Banana API

Nano Banana API 调用快速文生图，支持精准图内文字渲染和多角色一致性。

运行中 · 4 variants · 起价 $0.040

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-edit",
  "prompt": "创建一张励志海报，粗体衬线字写上 'Never Give Up'，背景是日落山脉。"
}'

import { NanoBananaClient } from "@runapi.ai/nano-banana";

const client = new NanoBananaClient();
const result = await client.textToImage.run({
    model: "nano-banana-edit",
    prompt: "创建一张励志海报，粗体衬线字写上 'Never Give Up'，背景是日落山脉。",
});

<?php

require __DIR__ . "/vendor/autoload.php";

use RunApi\NanoBanana\NanoBananaClient;

$client = new NanoBananaClient();
$result = $client->textToImage->run([
        'model' => 'nano-banana-edit',
        'prompt' => '创建一张励志海报，粗体衬线字写上 \'Never Give Up\'，背景是日落山脉。',
]);

require "runapi/nano_banana"

client = RunApi::NanoBanana::Client.new
result = client.text_to_image.run(
    model: "nano-banana-edit",
    prompt: "创建一张励志海报，粗体衬线字写上 'Never Give Up'，背景是日落山脉。"
)

npx skills add runapi-ai/nano-banana -g

# Claude Code
claude mcp add runapi -s user -- npx -y @runapi.ai/mcp

# Codex
codex plugin install runapi-mcp@agents

# Cursor / Windsurf / VS Code
npx @runapi.ai/mcp init cursor

@runapi.ai/nano-banana v1

概览

Nano Banana 是 Google 的快速图像生成模型，专为图内文字精准渲染和多角色场景一致性而优化，在保持提示词还原度的同时实现快速出图。

多变体覆盖不同速度/质量层级
Model skill 包含文档、schema 和接入说明
适合面向应用的编码工作流
失败的生成不计费

变体

对比全部 API 变体

Variant	Billing	From
nano-banana	call	$0.040	查看 →
nano-banana-2	call	$0.080	查看 →
nano-banana-edit	call	$0.040	查看 →
nano-banana-pro	call	$0.180	查看 →

技能

为应用开发安装 Nano Banana skill

把模型文档、schema、定价说明和接入步骤加载进代码工作区。

# Install the model skill for app development workflows
npx skills add runapi-ai/nano-banana -g

Installs docs, schemas, pricing context, and setup notes into your developer workspace.

Or use this setup request in your coding tool:

Install the Nano Banana skill for this app:

1. Add runapi-ai/nano-banana with the skills installer.
2. Load SKILL.md in this workspace.
3. Use its docs, schemas, pricing notes, and setup steps when adding model features.
4. Confirm the install path when done.

OpenClaw