MCP / Models / Text to video
LTX 2.5 Fast Text to Video MCP: quick drafts up to 4K
LTX 2.5 Fast turns a prompt into a 6 to 20 second video with synchronized sound, from 720p up to 4K, built for quick iteration. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

$ YOUR NEXT RUN
Use LTX 2.5 Fast Text to Video in your assistant
Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/ltx-2-5-fast-text-to-video.md. Help me connect the FlyMy.AI MCP to this assistant, then run LTX 2.5 Fast Text to Video (flymyai/ltx-2_5-fast-text-to-video) for this task: Make a 10-second 9:16 video of a hot air balloon rising over misty hills with LTX 2.5 Fast Text to Video at 1080p.
What LTX 2.5 Fast Text to Video does
One pass makes the video and its synchronized sound from prompt, up to 5,000 characters. duration is 6 to 20 seconds in steps of 2 (6 by default), resolution is 720p, 1080p (the default), 1440p or 2160p, which is 4K, aspect_ratio is 16:9 or 9:16, fps is 24, 25 (the default), 48 or 50, generate_audio is on by default and camera_motion adds one camera move. Clips over 10 seconds need 720p or 1080p at 24 or 25 fps; 1440p, 4K and 48 or 50 fps take up to 10 seconds. Output: video, one MP4 clip. Use it for drafts, social clips, storyboards and ideas tested in volume; for a final, high-fidelity render use LTX 2.5 Pro Text to Video.
It is billed per second of video, more at a higher resolution, and the same with or without sound and at any frame rate; you always choose the length, so the price is known before the run. It works from text (LTX 2.5 Fast Image to Video starts from a picture). It does not pick the length itself, edit or extend a video or take reference pictures or videos.
LTX 2.5 Fast Text to Video inputs
Every input of flymyai/ltx-2_5-fast-text-to-video as its live schema lists them. Returns video (array).
| Input | Type, values and default |
|---|---|
# prompt | string required Describe the video: the scene, the action, the camera, what people say and the sound |
# duration | integer optional Allowed: 6 to 20 Default: 6 Length of the clip in seconds: 6, 8, 10, 12, 14, 16, 18 or 20; the price is per second. Over 10 seconds needs 720p or 1080p at 24 or 25 fps |
# resolution | string optional Allowed: 720p, 1080p, 1440p, 2160p Default: 1080p 720p ($0.09 a second), 1080p ($0.13), 1440p ($0.19) or 2160p, which is 4K ($0.30) |
# aspect_ratio | string optional Allowed: 16:9, 9:16 Default: 16:9 Shape of the video: 16:9 or 9:16 |
# fps | integer optional Allowed: 24 to 50 Default: 25 Frames per second: 24, 25, 48 or 50; the price does not change. 48 and 50 take clips of up to 10 seconds |
# generate_audio | boolean optional Default: true Generate sound with the video (speech, ambience, effects); off makes a silent clip. The price is the same either way |
# camera_motion | string optional Allowed: dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down, static, focus_shift Optional camera move: dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down, static or focus_shift |
Ask your agent
Requests to paste as they are, once the FlyMy.AI MCP is connected.
flymyai/ltx-2_5-fast-text-to-videoflymyai/ltx-2_5-fast-text-to-videoflymyai/ltx-2_5-fast-text-to-videoLTX 2.5 Fast Text to Video price
From $0.09 per second of duration, depending on resolution. A run at the default settings costs $0.78. A run costs $0.54 to $3.00, depending on duration and resolution. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.
| Setting | Price |
|---|---|
| resolution 720p | $0.09 per second |
| resolution 1080p | $0.13 per second |
| resolution 1440p | $0.19 per second |
| resolution 2160p | $0.30 per second |
Call LTX 2.5 Fast Text to Video from code
The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.
From an agent, through the MCP
The agent calls get_model_schema, then run_model with:
{
"endpoint_id": "flymyai/ltx-2_5-fast-text-to-video",
"input": {
"prompt": "Steam rises from a ceramic mug on a sunlit kitchen counter, slow camera push-in"
}
}From your code, over HTTP
Form fields, not JSON; files go as uploads or public URLs. The answer is a prediction_id; read the result at https://api.flymy.ai/api/v1/flymyai/ltx-2_5-fast-text-to-video/predict/async/result/?request_id=<prediction_id>.
curl -X POST https://api.flymy.ai/api/v1/flymyai/ltx-2_5-fast-text-to-video/predict/async/ \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-F 'prompt=Steam rises from a ceramic mug on a sunlit kitchen counter, slow camera push-in'Questions about LTX 2.5 Fast Text to Video
Do I need a Lightricks API key for LTX 2.5 Fast Text to Video?
No. LTX 2.5 Fast Text to Video runs on FlyMy.AI's account, so you need no Lightricks key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.
How much does LTX 2.5 Fast Text to Video cost?
From $0.09 per second of duration, depending on resolution. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.
How do I use LTX 2.5 Fast Text to Video in Claude Code, Codex or Cursor?
Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Make a 10-second 9:16 video of a hot air balloon rising over misty hills with LTX 2.5 Fast Text to Video at 1080p." Your agent reads the inputs with get_model_schema and runs flymyai/ltx-2_5-fast-text-to-video with run_model.
What does LTX 2.5 Fast Text to Video need as input?
LTX 2.5 Fast Text to Video requires prompt; it also takes 6 optional inputs, each listed on this page with its allowed values and default.
Can I call LTX 2.5 Fast Text to Video from my own code?
Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/ltx-2_5-fast-text-to-video/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.
Go to the source
From the FlyMy.AI model catalog of 2026-11-18: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.





