# Sana text to image fal AI

Needs prompt.

Sana, served by fal.ai. $0.001 per megapixels Output is constrained to 1024x1024 and one image; reservation covers two billed megapixels, including whole-megapixel rounding. The exact receipt determines the final charge. Asynchronous: returns a request_id; poll fal/status and fetch fal/result with model "fal-ai/sana" and that request_id. The exact endpoint/request billing receipt is required before settlement.

- Tool ID: `fal/fal-ai-sana`
- Name in the catalog: Sana, text to image
- Provider: [fal.ai](/providers/fal.md)
- Capability: [AI image generation](/tools/image-generation.md)
- Price: $0.002 per call
- 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_call",
  "amountUsd": 0.002
}
```

Pricing source: [https://fal.ai/models/fal-ai/sana/llms.txt](https://fal.ai/models/fal-ai/sana/llms.txt). $0.001 per megapixels Output is constrained to 1024x1024 and one image; reservation covers two billed megapixels, including whole-megapixel rounding. The exact receipt determines the final charge..

Price verification date: 2026-11-03.

## Complete input schema


```json
{
  "type": "object",
  "properties": {
    "guidance_scale": {
      "title": "Guidance scale (CFG)",
      "maximum": 20,
      "type": "number",
      "description": "\n            The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.\n        ",
      "minimum": 0,
      "default": 5
    },
    "seed": {
      "description": "\n            The same seed and the same prompt given to the same version of the model\n            will output the same image every time.\n        ",
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "title": "Seed"
    },
    "num_images": {
      "title": "Num Images",
      "maximum": 1,
      "type": "integer",
      "description": "The number of images to generate.",
      "minimum": 1,
      "default": 1,
      "enum": [
        1
      ]
    },
    "negative_prompt": {
      "description": "\n            The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).\n        ",
      "type": "string",
      "title": "Negative Prompt",
      "default": ""
    },
    "prompt": {
      "description": "The prompt to generate an image from.",
      "type": "string",
      "title": "Prompt"
    },
    "enable_safety_checker": {
      "description": "If set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked, and images flagged as unsafe are returned as black images.",
      "type": "boolean",
      "title": "Enable Safety Checker",
      "default": true
    },
    "image_size": {
      "type": "object",
      "properties": {
        "width": {
          "type": "integer",
          "enum": [
            1024
          ]
        },
        "height": {
          "type": "integer",
          "enum": [
            1024
          ]
        }
      },
      "required": [
        "width",
        "height"
      ],
      "additionalProperties": false,
      "default": {
        "width": 1024,
        "height": 1024
      }
    },
    "output_format": {
      "enum": [
        "jpeg",
        "png"
      ],
      "description": "The format of the generated image.",
      "type": "string",
      "title": "Output Format",
      "default": "jpeg"
    },
    "num_inference_steps": {
      "title": "Num Inference Steps",
      "maximum": 50,
      "type": "integer",
      "description": "The number of inference steps to perform.",
      "minimum": 1,
      "default": 18,
      "enum": [
        18
      ]
    },
    "style_name": {
      "enum": [
        "(No style)",
        "Cinematic",
        "Photographic",
        "Anime",
        "Manga",
        "Digital Art",
        "Pixel art",
        "Fantasy art",
        "Neonpunk",
        "3D Model"
      ],
      "description": "The style to generate the image in.",
      "type": "string",
      "title": "Style Name",
      "default": "(No style)"
    }
  },
  "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/fal-ai-sana",
  "input": {
    "prompt": "Underwater coral reef ecosystem during peak bioluminescent activity, multiple layers of marine life - from microscopic plankton to massive coral structures, light refracting through crystal-clear tropical waters, creating prismatic color gradients, hyper-detailed texture of marine organisms",
    "image_size": {
      "width": 1024,
      "height": 1024
    },
    "num_images": 1,
    "num_inference_steps": 18,
    "guidance_scale": 5,
    "negative_prompt": "",
    "enable_safety_checker": true,
    "output_format": "jpeg",
    "style_name": "(No style)"
  }
}
```

## 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/sana)

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

---

[HTML page](/providers/fal/fal-ai-sana) · [Agent index](/llms.txt)