HappyHorse 1.0 Coming SoonLearn More
EvoLink.AIEvoLink.AI

Nano Banana 2 API

Access Nano Banana 2 through EvoLink for Gemini 3.1 Flash Image generation and editing, with lower pricing than the Google official route, OpenAI-compatible requests, and no Google Cloud setup.
Model Type:
✓Nano Banana 2Nano Banana 2 Beta

Price: $0.042 - 0.141(~ 2.8398 - 9.5801 credits) per image

Output image only. Input image and web search charged separately.

Highest stability with guaranteed 99.9% uptime. Recommended for production environments.

Use the same API endpoint for all versions. Only the model parameter differs.

Nano Banana 2 API Pricing, Access, and Integration

Use Gemini 3.1 Flash Image through EvoLink with clear 1K, 2K, and 4K pricing, OpenAI-compatible integration, and no Google Cloud project or billing setup.

Nano Banana 2 pricing starts at $0.0538 for 1K, $0.0806 for 2K, and $0.1210 for 4K on EvoLink. That is up to 20% lower than the Google official route, with OpenAI-compatible requests and no Google Cloud project or billing setup.

Save 10-20% vs Google's standard API pricingNo Google Cloud account or billing setup requiredOne API key for Nano Banana 2 + 200 other AI models
Hero showcase of AI image editing feature 1
550 (suggested: 2,000)

Upload up to 14 images (max 20MB each)

Click to upload or drag and drop

Supported formats: JPEG, JPG, PNG, WEBP
Maximum file size: 20MB; Maximum files: 14

Generated image 1

History

Max 20 items

0 running · 0 completed

Your generation history will appear here

Billing Rules

  • •Output image price varies by quality (0.5K/1K/2K/4K)
  • •Reference images: charged per image uploaded
  • •Web search: charged per request when enabled. A single request may trigger multiple searches.

Pricing

Nano Banana 2
Input Image
quality:Reference
Price:
$0.0005/ image
(0.0355 Credits)
Nano Banana 2
Output Image
quality:0.5K
Price:
$0.042/ image
(2.8398 Credits)
Nano Banana 2
Output Image
quality:1K
Price:
$0.063/ image
(4.2578 Credits)
Nano Banana 2
Output Image
quality:2K
Price:
$0.094/ image
(6.3867 Credits)
Nano Banana 2
Output Image
quality:4K
Price:
$0.141/ image
(9.5801 Credits)
Nano Banana 2
Web Search
Price:
$0.013/ request
(0.8871 Credits)

If it's down, we automatically use the next cheapest available—ensuring 99.9% uptime at the best possible price.

Capabilities of the Nano Banana 2 API

Semantic edits from plain language

The Nano Banana 2 API understands intent — "remove the glare," "swap the mug for a glass," "make the background warmer." Built on Gemini 3.1 Flash's reasoning engine, it applies changes while preserving the rest of the scene. No masks, no layers. Describe the outcome, get the result. Ideal for ecommerce cleanup, content refreshes, and social ad variations.

Start using API
Workflow showcase of AI image editing feature 2

Accurate text rendering and localization

Nano Banana 2 delivers strong text rendering accuracy — a key improvement over earlier Flash models. Posters, menus, price cards, UI mockups, and multilingual assets stay readable after generation and editing. Replace wording, adjust labels, and maintain layout balance across languages without rebuilding every design.

Start using API
Workflow showcase of AI image editing feature 3

Multi-image fusion for consistent identity

Maintain up to 5 characters and 14 objects in a single workflow. Keep a character, mascot, or product visually aligned across scenes, angles, and backgrounds. Gemini 3.1 Flash Image's composition understanding makes catalog shoots, ad series, and brand campaigns scalable without manual consistency checks.

Start using API
Workflow showcase of AI image editing feature 4

Why developers choose Nano Banana 2 API

Built on Gemini 3.1 Flash Image preview, Nano Banana 2 API delivers reliable edits, clear text rendering, and multi-image consistency, with official and Lite routes to balance stability and cost.

Flash-speed inference

Built on the Gemini 3.1 Flash architecture, Nano Banana 2 delivers Pro-level world knowledge, quality and reasoning at Flash speed. Faster generation means tighter feedback loops for interactive applications and batch workflows.

Production-grade 4K resolution

Generate 1K, 2K, or native 4K outputs with legible text. Posters, menus, diagrams, and UI mockups ship without extra cleanup or upscaling.

One key, zero setup

Access Nano Banana 2 through EvoLink with a single API key. No Google Cloud project, no billing configuration, no quota requests. Same OpenAI-compatible format you already use.

How to integrate the Nano Banana 2 API

Send an image, describe the change, and receive a ready-to-use result.

1

Step 1 — Get your API key

Sign up on EvoLink (free), grab your API key from the dashboard. Works with Nano Banana 2 and 200+ other models instantly.

2

Step 2 — Send your request

POST to the EvoLink endpoint with your image (URL or Base64), prompt, and optional reference images. OpenAI-compatible format — minimal code changes if you're migrating from another provider.

3

Step 3 — Review and deploy

Receive the generated or edited image. Save to your storage, publish across channels. Scale up with batch processing when ready.

Open API Playground

Key features of the Nano Banana 2 API

Built for editing-heavy production workflows

Control

Instruction-based semantic editing

The Nano Banana 2 API turns short prompts into targeted edits such as remove, replace, or restyle while preserving composition, so teams avoid manual masking and keep iteration fast.

Text

Clear text inside images

Gemini 3.1 Flash Image is built to render readable text for posters, menus, diagrams, and UI mockups, helping Nano Banana 2 API outputs stay legible across languages and formats.

Consistency

Multi-image fusion (up to 14)

Blend multiple references in one Nano Banana 2 API request to keep people, products, and visual style consistent across a series of edits or variations.

Look

Lighting and color adjustments

Refine mood by changing color grades, lighting direction, or day and night settings. This is useful for brand style alignment and seasonal campaigns.

Resolution

1K to 4K output options

Generate 1K, 2K, or 4K results and upscale for delivery, keeping edges crisp for web, apps, and print-ready assets.

Cost

Official and Lite routing

Choose the official Gemini 3.1 Flash Image preview route for stability, or use the Nano Banana 2 Lite route for lower cost when you can trade some control.

Nano Banana 2 API FAQs

Everything you need to know about the product and billing.

Nano Banana 2 is the community name for Google's Gemini 3.1 Flash Image model (model ID: gemini-3.1-flash-image-preview). It combines Flash-speed inference with high-quality image generation and editing, supporting up to 4K resolution and multi-image consistency. Nano Banana 2 officially launched on February 26, 2026, rolling out across Gemini app, Google Search, AI Studio, Vertex AI, and Flow.
Google's official pricing is $0.101 per 2K image and $0.15 per 4K image. Through EvoLink, Nano Banana 2 costs $0.0806 per 2K image and $0.1210 per 4K image — saving you 20%.
Nano Banana Pro is based on Gemini 3.1 Flash Image — optimized for maximum quality. Nano Banana 2 is based on Gemini 3.1 Flash Image — optimized for speed while approaching Pro-level quality. Nano Banana 2 offers lower latency and cost for most production use cases. Nano Banana 2 is now the default image model in the Gemini app, replacing Nano Banana Pro. Pro remains available for specialized high-fidelity tasks via the regenerate menu.
Sign up on EvoLink, get an API key, and call the Nano Banana 2 endpoint. No Google Cloud account needed. EvoLink provides OpenAI-compatible endpoints, so integration takes minutes.
Yes. Nano Banana 2 is the community name for Google's Gemini 3.1 Flash Image model. The model ID is gemini-3.1-flash-image-preview.
Nano Banana 2 supports native 1K, 2K, and 4K image generation. Higher resolutions cost more per image. 4K output produces print-ready images with legible text.
EvoLink offers free trial credits for new accounts, so you can test Nano Banana 2 at no cost. Google AI Studio also provides a limited free tier for experimentation.
Nano Banana (original) runs on Gemini 2.5 Flash Image — fast but limited to lower resolution with inconsistent text. Nano Banana 2 runs on Gemini 3.1 Flash Image — a generational upgrade with 4K support, better text rendering, and multi-image fusion. You can maintain up to 5 characters and 14 objects in a single workflow.
The Beta version is experimental: lower cost, but not 100% guaranteed availability. If you hit this error: 1. Wait and retry: it usually recovers in 5-10 minutes. 2. Switch to the official version: change the model ID from nano-banana-2-beta to nano-banana-2. The official version provides 99.9% uptime
POST
/v1/images/generations

Generate Image

Create an image generation task using text prompts or reference images. Supports text-to-image, image-to-image, and image editing modes.

Asynchronous processing mode, use the returned task ID to .

Generated image links are valid for 24 hours, please save them promptly.

Request Parameters

modelstringRequiredDefault: gemini-3.1-flash-image-preview

Image generation model name.

ValueDescription
gemini-3.1-flash-image-previewNano Banana 2 model
Examplegemini-3.1-flash-image-preview
promptstringRequired

Prompt describing the image to be generated or how to edit the input image.

Notes
  • Limited to 2000 tokens
ExampleA cat playing in the grass
sizestringOptionalDefault: auto

Aspect ratio of the generated image.

ValueDescription
autoAuto detect
1:1Square (1:1)
1:4Tall vertical (1:4)
4:1Wide horizontal (4:1)
1:8Ultra-tall vertical (1:8)
8:1Ultra-wide horizontal (8:1)
2:3Portrait (2:3)
3:2Landscape (3:2)
3:4Portrait (3:4)
4:3Landscape (4:3)
4:5Portrait (4:5)
5:4Landscape (5:4)
9:16Vertical (9:16)
16:9Horizontal (16:9)
21:9Ultra-wide (21:9)
Notes
  • All listed aspect ratios are supported
Example16:9
qualitystringOptionalDefault: 2K

Quality of the generated image.

ValueDescription
0.5KDraft quality (lowest cost)
1KStandard quality
2KHigh quality (default)
4KUltra quality (Higher Cost)
Notes
  • Different quality levels have different pricing
Example2K
model_params.web_searchbooleanOptional

Whether to enable web search. When enabled, the model will use web search results to optimize image generation. Nested inside model_params object.

Exampletrue
model_params.thinking_levelstringOptionalDefault: auto

Thinking level, controls the depth of reasoning the model performs before generating images. Nested inside model_params object.

ValueDescription
autoAutomatically selects thinking level
minMinimal reasoning, fastest
highDeep reasoning, best quality
Exampleauto
image_urlsarrayOptional

Reference image URL list for image-to-image and image editing functions.

Notes
  • Max 14 images per request
  • Max size: 20MB per image
  • Formats: .jpeg, .jpg, .png, .webp
  • URLs must be directly accessible by the server
  • Maximum 4 real person images
Examplehttps://example.com/image1.png
callback_urlstringOptional

HTTPS callback address after task completion.

Notes
  • Triggered on completion, failure, or cancellation
  • Sent after billing confirmation
  • HTTPS only, no internal IPs
  • Max length: 2048 chars
  • Timeout: 10s, Max 3 retries
Examplehttps://your-domain.com/webhooks/image-task-completed

Request Example

{
  "model": "gemini-3.1-flash-image-preview",
  "prompt": "A cat playing on the grass",
  "size": "16:9",
  "quality": "2K",
  "model_params": {
    "web_search": true,
    "thinking_level": "auto"
  }
}

Response Example

{
  "created": 1757165031,
  "id": "task-unified-1757165031-uyujaw3d",
  "model": "gemini-3.1-flash-image-preview",
  "object": "image.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 45
  },
  "type": "image",
  "usage": {
    "billing_rule": "per_call",
    "credits_reserved": 1.6,
    "user_group": "default"
  }
}