# Bagel text to image fal AI

Needs prompt.

Bagel, served by fal.ai. $0.1 per images One submitted item is offered per call; the exact receipt determines the final charge. Asynchronous: returns a request_id; poll fal/status and fetch fal/result with model "fal-ai/bagel" and that request_id. The exact endpoint/request billing receipt is required before settlement.

- Tool ID: `fal/fal-ai-bagel`
- Name in the catalog: Bagel, text to image
- Provider: [fal.ai](/providers/fal.md)
- Capability: [AI image generation](/tools/image-generation.md)
- Price: $0.1 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": 0.1
}
```

Pricing source: [https://fal.ai/models/fal-ai/bagel/llms.txt](https://fal.ai/models/fal-ai/bagel/llms.txt). $0.1 per images One submitted item is offered per call; the exact receipt determines the final charge..

Price verification date: 2026-11-03.

## Complete input schema


```json
{
  "type": "object",
  "properties": {
    "seed": {
      "title": "Seed",
      "description": "The seed to use for the generation.",
      "type": "integer"
    },
    "enable_safety_checker": {
      "default": true,
      "title": "Enable Safety Checker",
      "description": "If set to true, the safety checker will be enabled.",
      "type": "boolean"
    },
    "prompt": {
      "title": "Prompt",
      "description": "The prompt to generate an image from.",
      "type": "string"
    },
    "use_thought": {
      "default": false,
      "title": "Use Thought",
      "description": "Whether to use thought tokens for generation. If set to true, the model will \"think\" to potentially improve generation quality. Increases generation time and increases the cost by 20%.",
      "type": "boolean",
      "enum": [
        false
      ]
    }
  },
  "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-bagel",
  "input": {
    "prompt": "A luminous ancient temple floating among cosmic clouds, with impossible architecture of twisted spires and inverted arches. The structure is half-built from crystalline white marble and half from living bioluminescent coral in vibrant teal and purple. Ethereal light filters through stained glass windows depicting mythological scenes. Tiny cloaked figures with glowing lanterns traverse impossible staircases. In the foreground, a massive ornate door stands slightly ajar, revealing a glimpse of swirling golden energy within. The scene is lit by two moons of different colors, casting overlapping shadows. Cinematic lighting, hyper-detailed textures, 8K resolution.",
    "use_thought": false,
    "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/bagel)

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

---

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