# Nano Banana 2 Flex MCP and API by Google | FlyMy.AI

> Nano Banana 2 Flex runs Google's Gemini 3.1 Image on Google's lower-priced flex tier, with the same inputs and outputs as Nano Banana 2.

Page: https://flymy.ai/mcp/models/nano-banana-2-flex-inference/

MCP / Models / Image generation

# Nano Banana 2 Flex MCP: lower-cost 4K images with no API key

Nano Banana 2 Flex runs Google's Gemini 3.1 Image on Google's lower-priced flex tier, with the same inputs and outputs as Nano Banana 2. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

[Use Nano Banana 2 Flex](https://flymy.ai/mcp/models/nano-banana-2-flex-inference/#start) [Inputs and price](https://flymy.ai/mcp/models/nano-banana-2-flex-inference/#inputs)

No API key, from $0.0355 / run, Text and image to image, Google, Commercial use

$ YOUR NEXT RUN

Claude Code, Codex, Cursor, Any agent

## Use Nano Banana 2 Flex in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

```
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/nano-banana-2-flex-inference.md. Help me connect the FlyMy.AI MCP to this assistant, then run Nano Banana 2 Flex (flymyai/nano-banana-2-flex-inference) for this task: Generate a 9:16 product photo of a smartwatch on a mossy rock in soft fog with Nano Banana 2 Flex at 4K.
```

[Open FlyMy.AI](https://app.flymy.ai/new-agent) [Download brief](https://flymy.ai/mcp/models/nano-banana-2-flex-inference.md)

## What Nano Banana 2 Flex does

Flex uses the same model and inputs as Nano Banana 2: prompt, image_urls for references, resolution 1K, 2K or 4K, 14 aspect ratios or auto, num_images up to 10, safety_tolerance and enable_web_search. Choose it for batches where the price per image matters most.

## Nano Banana 2 Flex inputs

Every input of `flymyai/nano-banana-2-flex-inference` as its live schema lists them. Returns `description` (string), `images` (array), `token_usage` (string).

| Input | Type, values and default |
|---|---|
| [#](https://flymy.ai/mcp/models/nano-banana-2-flex-inference/#input-prompt) `prompt` | string required |
| [#](https://flymy.ai/mcp/models/nano-banana-2-flex-inference/#input-aspect_ratio) `aspect_ratio` | string optional Allowed: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 4:1, 1:4, 8:1, 1:8, auto Default: `auto` |
| [#](https://flymy.ai/mcp/models/nano-banana-2-flex-inference/#input-resolution) `resolution` | string optional Allowed: 1K, 2K, 4K Default: `1K` |
| [#](https://flymy.ai/mcp/models/nano-banana-2-flex-inference/#input-image_urls) `image_urls` | array optional |
| [#](https://flymy.ai/mcp/models/nano-banana-2-flex-inference/#input-num_images) `num_images` | integer optional Allowed: 1 to 10 Default: `1` |
| [#](https://flymy.ai/mcp/models/nano-banana-2-flex-inference/#input-safety_tolerance) `safety_tolerance` | integer optional Allowed: 1 to 6 Default: `4` |
| [#](https://flymy.ai/mcp/models/nano-banana-2-flex-inference/#input-enable_web_search) `enable_web_search` | boolean optional Default: `false` |

## Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

**“Generate a 9:16 product photo of a smartwatch on a mossy rock in soft fog with Nano Banana 2 Flex at 4K.”** runs `flymyai/nano-banana-2-flex-inference`

**“Make three versions of a poster for a spring sale with 30% off with Nano Banana 2 Flex in one run and send me the links.”** runs `flymyai/nano-banana-2-flex-inference`

**“Use Nano Banana 2 Flex to place the product from the photo I attach on a marble bathroom counter at sunrise.”** runs `flymyai/nano-banana-2-flex-inference`

## Nano Banana 2 Flex price

From $0.0355 per run, depending on num_images and resolution. A run at the default settings costs $0.0355. A run costs $0.0355 to $0.757, depending on num_images and resolution. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

[See usage pricing →](https://flymy.ai/pricing/)

## Call Nano Banana 2 Flex from code

The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.

### From an agent, through the MCP

The agent calls `get_model_schema`, then `run_model` with:

```
{
  "endpoint_id": "flymyai/nano-banana-2-flex-inference",
  "input": {
    "prompt": "A ceramic mug on a sunlit kitchen counter, product photo"
  }
}
```

### From your code, over HTTP

Form fields, not JSON; files go as uploads or public URLs. The answer is a `prediction_id`; read the result at `https://api.flymy.ai/api/v1/flymyai/nano-banana-2-flex-inference/predict/async/result/?request_id=<prediction_id>`.

```
curl -X POST https://api.flymy.ai/api/v1/flymyai/nano-banana-2-flex-inference/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=A ceramic mug on a sunlit kitchen counter, product photo'
```

## Questions about Nano Banana 2 Flex

**Do I need a Google API key for Nano Banana 2 Flex?**

No. Nano Banana 2 Flex runs on FlyMy.AI's account, so you need no Google key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

**How much does Nano Banana 2 Flex cost?**

From $0.0355 per run, depending on num_images and resolution. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-09.

**How do I use Nano Banana 2 Flex in Claude Code, Codex or Cursor?**

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Generate a 9:16 product photo of a smartwatch on a mossy rock in soft fog with Nano Banana 2 Flex at 4K." Your agent reads the inputs with get_model_schema and runs flymyai/nano-banana-2-flex-inference with run_model.

**What does Nano Banana 2 Flex need as input?**

Nano Banana 2 Flex requires prompt; it also takes 6 optional inputs, each listed on this page with its allowed values and default.

**Can I call Nano Banana 2 Flex from my own code?**

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/nano-banana-2-flex-inference/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.

## More image generation models

Text to image: product shots, ads, posters and illustrations from a prompt, many with reference images.

### Nano Banana 2.1

Gemini's newest image model: 14 references, up to 4K, with adjustable thinking.

Text and image to image / from $0.0336 / image

Link: https://flymy.ai/mcp/models/nano-banana-2-1/

### Nano Banana 2 Lite

The cheapest Nano Banana 2 tier: 1K images in volume with the same prompt understanding.

Text and image to image / from $0.0376 / run

Link: https://flymy.ai/mcp/models/nano-banana-2-lite/

### Nano Banana 2

Gemini 3.1 Image: up to 10 images per run at up to 4K, with optional web search.

Text and image to image / from $0.071 / run

Link: https://flymy.ai/mcp/models/nano-banana-2/

### Nano Banana Pro

Gemini 3 Pro Image for posters, packaging and logos where the words must be right.

Text and image to image / from $0.15 / run

Link: https://flymy.ai/mcp/models/nano-banana-pro/

### Nano Banana

The original Gemini 2.5 image model: quick drafts and conversational edits.

Text and image to image / $0.039 / run

Link: https://flymy.ai/mcp/models/nano-banana/

### Imagen 4

Google's standard Imagen 4: realistic images, up to four per run, with SynthID marking.

Text to image / $0.04 / run

Link: https://flymy.ai/mcp/models/imagen-4/

## Go to the source

[Nano Banana 2 Flex in the playground →](https://app.flymy.ai/models/flymyai/nano-banana-2-flex-inference), [Model endpoints in the docs →](https://docs.flymy.ai/api/models-endpoints), [Image generation guide →](https://docs.flymy.ai/guides/generate-images), [Every model on FlyMy.AI →](https://flymy.ai/mcp/models/), [Every MCP in the catalog →](https://flymy.ai/mcp/#catalog), [Usage pricing →](https://flymy.ai/pricing/)

From the FlyMy.AI model catalog of 2026-11-09: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.

---

For agents: the FlyMyAI operating guide (sign up, connect, run models, tools and agents) is https://flymy.ai/skill.md, and https://flymy.ai/llms.txt lists the other pages and the documentation.