# FLUX.2 \[klein\] 9B Base text to image fal AI

Needs prompt.

FLUX.2 [klein] 9B Base, served by fal.ai. $0.011 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/flux-2" and that request_id. The exact endpoint/request billing receipt is required before settlement.

- Tool ID: `fal/fal-ai-flux-2-klein-9b-base`
- Name in the catalog: FLUX.2 \[klein\] 9B Base, text to image
- Provider: [fal.ai](/providers/fal.md)
- Capability: [FLUX.2](/tools/image-generation/flux.md)
- Price: $0.022 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": 0.022
}
```

Pricing source: [https://fal.ai/models/fal-ai/flux-2/klein/9b/base/llms.txt](https://fal.ai/models/fal-ai/flux-2/klein/9b/base/llms.txt). $0.011 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": {
    "prompt": {
      "title": "Prompt",
      "description": "The prompt to generate an image from.",
      "type": "string"
    },
    "seed": {
      "title": "Seed",
      "description": "The seed to use for the generation. If not provided, a random seed will be used.",
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ]
    },
    "guidance_scale": {
      "minimum": 0,
      "default": 5,
      "description": "Guidance scale for classifier-free guidance.",
      "title": "Guidance Scale",
      "type": "number",
      "maximum": 20
    },
    "num_inference_steps": {
      "minimum": 4,
      "default": 28,
      "description": "The number of inference steps to perform.",
      "title": "Number of Inference Steps",
      "type": "integer",
      "maximum": 50,
      "enum": [
        28
      ]
    },
    "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": {
      "title": "Output Format",
      "default": "png",
      "description": "The format of the generated image.",
      "type": "string",
      "enum": [
        "jpeg",
        "png",
        "webp"
      ]
    },
    "acceleration": {
      "title": "Acceleration",
      "default": "regular",
      "description": "The acceleration level to use for image generation.",
      "type": "string",
      "enum": [
        "regular"
      ]
    },
    "negative_prompt": {
      "title": "Negative Prompt",
      "default": "",
      "description": "Negative prompt for classifier-free guidance. Describes what to avoid in the image.",
      "type": "string"
    },
    "num_images": {
      "minimum": 1,
      "default": 1,
      "description": "The number of images to generate.",
      "title": "Number of Images",
      "type": "integer",
      "maximum": 1,
      "enum": [
        1
      ]
    },
    "enable_safety_checker": {
      "title": "Enable Safety Checker",
      "default": true,
      "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"
    }
  },
  "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-flux-2-klein-9b-base",
  "input": {
    "prompt": "A cyberpunk samurai standing in neon-lit Tokyo street at night, rain-soaked pavement reflecting holographic advertisements in pink and blue, steam rising from street vents, wearing futuristic armor with glowing accents, cinematic composition, Unreal Engine 5 quality, ray-traced reflections, shallow depth of field, hyper-detailed",
    "image_size": {
      "width": 1024,
      "height": 1024
    },
    "num_images": 1,
    "num_inference_steps": 28,
    "acceleration": "regular",
    "guidance_scale": 5,
    "output_format": "png",
    "negative_prompt": "",
    "enable_safety_checker": true
  }
}
```

## 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/flux-2/klein/9b/base)

[REST inspection](https://api.agentik.cc/v1/tools/fal/fal-ai-flux-2-klein-9b-base) · [OpenAPI](/openapi.json) · [Connection guide](/connect.md)

---

[HTML page](/providers/fal/fal-ai-flux-2-klein-9b-base) · [Agent index](/llms.txt)