# Nano Banana 2 image edit

Needs prompt. Served by fal.ai.

Nano Banana 2 (Google), image edit, served by fal.ai. The OpenAPI schema for the fal-ai/nano-banana-2/edit queue. Price: $0.08 per image; +$0.015 per call with web search; +$0.002 with high thinking. Waits up to 40 s for the result; if the generation takes longer, the run stays RUNNING and returns a request_id; poll fal/status and fetch fal/result with model "fal-ai/nano-banana-2" and that request_id. Billed once, when the result is ready; a generation that fails is refunded.

- Tool ID: `fal/nano-banana-2-edit`
- Name in the catalog: Nano Banana 2 (Google), image edit
- Provider: [fal.ai](/providers/fal.md)
- Capability: [Nano Banana](/tools/image-generation/nano-banana.md)
- Price: from $0.08 per image
- Authentication: an authorised Agentik workspace is required for execution, including zero-price tools.

## Pricing contract

The provider’s price, with no markup. Billed for measured usage.


```json
{
  "model": "per_unit",
  "amountUsd": 0.08,
  "unitsField": "num_images",
  "unitsDefault": 1,
  "maxUnits": 4,
  "multipliers": [
    {
      "when": {
        "field": "enable_web_search",
        "truthy": true
      },
      "addUsd": 0.015
    },
    {
      "when": {
        "field": "thinking_level",
        "equals": "high"
      },
      "addUsd": 0.002
    }
  ]
}
```

Pricing source: [https://fal.ai/models/fal-ai/nano-banana-2/edit](https://fal.ai/models/fal-ai/nano-banana-2/edit). $0.08 per image; +$0.015 per call with web search; +$0.002 with high thinking..

Price verification date: 2026-10-08.

## Complete input schema


```json
{
  "type": "object",
  "properties": {
    "video_url": {
      "type": "string",
      "description": "Optional video to use as input context. Accepts an http(s)/data URL to a video file (downloaded and sent inline, max 15MB) or a YouTube URL (passed through to the model without downloading).",
      "title": "Video URL"
    },
    "audio_url": {
      "type": "string",
      "description": "Optional audio file to use as input context. Accepts an http(s)/data URL (downloaded and sent inline, max 15MB).",
      "title": "Audio URL"
    },
    "pdf_url": {
      "type": "string",
      "description": "Optional PDF document to use as input context. Accepts an http(s)/data URL (downloaded and sent inline, max 15MB).",
      "title": "PDF URL"
    },
    "safety_tolerance": {
      "default": "4",
      "enum": [
        "1",
        "2",
        "3",
        "4",
        "5",
        "6"
      ],
      "description": "The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.",
      "title": "Safety Tolerance",
      "type": "string"
    },
    "limit_generations": {
      "default": true,
      "description": "Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate and ignore any intermediate images generated by the model. This may affect generation quality.",
      "title": "Limit Generations",
      "type": "boolean"
    },
    "resolution": {
      "default": "1K",
      "enum": [
        "0.5K",
        "1K",
        "2K",
        "4K"
      ],
      "description": "The resolution of the image to generate.",
      "title": "Resolution",
      "type": "string"
    },
    "system_prompt": {
      "default": "",
      "description": "Optional system instruction that steers the model's persona and output style across the request. Leave blank to omit; when provided, it is sent as the system instruction to Gemini (or as a system message on OpenAI-compatible providers).",
      "title": "System Prompt",
      "type": "string",
      "maxLength": 50000
    },
    "image_urls": {
      "title": "Image URLs",
      "description": "The URLs of the images to use for image-to-image generation or image editing. Optional when at least one of `video_url`, `audio_url`, or `pdf_url` is provided.",
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "aspect_ratio": {
      "enum": [
        "auto",
        "21:9",
        "16:9",
        "3:2",
        "4:3",
        "5:4",
        "1:1",
        "4:5",
        "3:4",
        "2:3",
        "9:16",
        "4:1",
        "1:4",
        "8:1",
        "1:8"
      ],
      "type": "string",
      "default": "auto",
      "description": "The aspect ratio of the generated image. Supports extreme ratios: 4:1, 1:4, 8:1, 1:8.",
      "title": "Aspect Ratio"
    },
    "seed": {
      "type": "integer",
      "description": "The seed for the random number generator.",
      "title": "Seed"
    },
    "enable_web_search": {
      "default": false,
      "description": "Enable web search for the image generation task. This will allow the model to use the latest information from the web to generate the image.",
      "title": "Enable Web Search",
      "type": "boolean"
    },
    "output_format": {
      "default": "png",
      "enum": [
        "jpeg",
        "png",
        "webp"
      ],
      "description": "The format of the generated image.",
      "title": "Output Format",
      "type": "string"
    },
    "num_images": {
      "minimum": 1,
      "default": 1,
      "description": "The number of images to generate.",
      "maximum": 4,
      "type": "integer",
      "title": "Number of Images"
    },
    "prompt": {
      "maxLength": 50000,
      "title": "Prompt",
      "minLength": 3,
      "description": "The prompt for image editing.",
      "type": "string"
    },
    "thinking_level": {
      "enum": [
        "minimal",
        "high"
      ],
      "type": "string",
      "description": "When set, enables model thinking with the given level ('minimal' or 'high') and includes thoughts in the generation. Omit to disable.",
      "title": "Thinking Level"
    }
  },
  "required": [
    "prompt"
  ],
  "additionalProperties": false
}
```

## Published example

This is the provider tool’s published example. Replace example values with the user’s requested inputs, respecting the schema; do not execute an example merely to test a connection.


```json
{
  "tool_id": "fal/nano-banana-2-edit",
  "input": {
    "prompt": "make the cube blue, keep everything else",
    "image_urls": [
      "https://storage.googleapis.com/falserverless/example_outputs/nano-banana-2-t2i-output.png"
    ],
    "num_images": 1,
    "resolution": "0.5K"
  }
}
```

## Execute and retrieve

Inspect again before execution, explain the price and obtain the required authority. Use MCP run_tool or POST /v1/run with this tool ID, valid input and an idempotency key. Save the returned run ID and follow the actual state. If Agentik answers that the tool is temporarily unavailable, do not retry it blindly; use discovery to propose an alternative.

This tool uses deferred settlement. Follow its returned task/run instructions; preserve the existing reservation until the result is reconciled.

A partial or uncertain result can still have consumed provider resources. Consult [billing](/docs/billing.md), [idempotency](/docs/idempotency.md) and [asynchronous results](/docs/async.md).

[Provider documentation](https://fal.ai/models/fal-ai/nano-banana-2/edit)

[REST inspection](https://api.agentik.cc/v1/tools/fal/nano-banana-2-edit) · [OpenAPI](/openapi.json) · [Connection guide](/connect.md)

---

[HTML page](/providers/fal/nano-banana-2-edit) · [Agent index](/llms.txt)