Lightricks · fal.ai · Text to video
LTX 2.5 Pro
LTX 2.5 Pro (Lightricks), text to video, served by fal.ai. The OpenAPI schema for the lightricks/ltx-2.5/text-to-video/pro queue. Price: $0.12 per second at 720p, $0.17 at 1080p (default). Asynchronous: returns a request_id; poll fal/status and fetch fal/result with model "lightricks/ltx-2.5".
Usage based fal.aiVideofal/ltx-2-5-pro-text-to-videoListed
Activation pending; your agent will see it as unavailable until then.
Use this tool with your agent
Give this to your agent
Use my connected Agentik MCP server. I want to use the tool fal/ltx-2-5-pro-text-to-video (LTX 2.5 Pro (Lightricks), text to video). Call inspect_tool with {"tool_id": "fal/ltx-2-5-pro-text-to-video"} first and tell me the price before anything runs. Ask me for the inputs it needs; never invent values, IDs or file URLs. When I confirm, call run_tool with tool_id "fal/ltx-2-5-pro-text-to-video" and my inputs, follow it with get_run if it is still running, and give me the result and the price Agentik reports. If the tool is unavailable, say so and use discover_tools to propose an alternative.Show the prompt
Paste it into Claude, ChatGPT or Codex: your agent takes it from there, and shows the price before it runs.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
aspect_ratio | string | No | The aspect ratio of the generated video Options: 16:9, 9:16. |
duration | integer | No | The duration of the generated video in seconds, up to 10 seconds. Set to 'auto' to let the model choose the duration automatically. Options: 6, 8, 10. |
prompt | string | Yes | The prompt to use for the generated video |
generate_audio | boolean | No | Whether to generate audio for the generated video |
fps | integer | No | The frames per second of the generated video. Options: 24, 25, 50. |
resolution | string | No | The resolution of the generated video. Options: 720p, 1080p. |
camera_motion | string | No | Optional camera motion applied to the generated video. Options: dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down, static, focus_shift. |
How your agent calls it
First inspect_tool for the current schema and price, then run_tool with the published example after confirming your inputs:
{
"tool_id": "fal/ltx-2-5-pro-text-to-video",
"input": {
"prompt": "a red cube slowly rotating on a white table, soft studio light",
"duration": 6,
"resolution": "720p",
"generate_audio": false
}
}Price and billing
- Price
- Usage based
- Model
- Per unit
- Detail
- The provider’s price, with no markup. Billed for measured usage.
- The provider’s price, 0% markup.
- One prepaid balance for every provider; your agent sees the price before it runs.
- Pay for measured usage; unused reservations are released.