LTX API pricing

Usage-based pricing by endpoint and output quality.

Model version
Model type
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

Text-to-Video

LTX-2.3
Pro

Optimized for higher fidelity and increased temporal stability. Best for production-ready output and final renders.

URL path:
/v2/text-to-video (async) · /v1/text-to-video (sync)
Pricing:
  • 1280×720 — $0.04/sec
  • 1920×1080 — $0.08/sec
  • 2560×1440 — $0.16/sec
  • 3840×2160 — $0.32/sec
Notes:
  • Ideal for client-facing content or polished deliverables.
  • Higher compute level → higher visual quality.

Text-to-Video

LTX-2.3
Fast

Designed for quick iteration, previews, and fast creative exploration.

URL path:
/v2/text-to-video (async) · /v1/text-to-video (sync)
Pricing:
  • 1280×720 — $0.03/sec
  • 1920×1080 — $0.06/sec
  • 2560×1440 — $0.12/sec
  • 3840×2160 — $0.24/sec
Notes:
  • Same pricing applies for text input and pure prompt-based generation.

Text-to-Video

LTX-2.5
Fast

Designed for quick iteration, previews, and fast creative exploration.

URL path:
/v2/text-to-video (async) · /v1/text-to-video (sync)
Pricing:
  • 1280×720 — $0.09/sec
  • 1920×1080 — $0.13/sec
  • 2560×1440 — $0.19/sec
  • 3840×2160 — $0.30/sec
Notes:
  • Same pricing applies for text input and pure prompt-based generation.

Text-to-Video

LTX-2.5
Pro

Optimized for higher fidelity and increased temporal stability. Best for production-ready output and final renders.

URL path:
/v2/text-to-video (async) · /v1/text-to-video (sync)
Pricing:
  • 1280×720 — $0.12/sec
  • 1920×1080 — $0.17/sec
  • 2560×1440 — $0.25/sec
  • 3840×2160 — $0.39/sec
Notes:
  • Ideal for client-facing content or polished deliverables.
  • Higher compute level → higher visual quality.

Image-to-Video

LTX-2.3
Pro

For detailed, stable motion derived from a still image. Best for high-quality sequences, storytelling, and production use.

URL path:
/v2/image-to-video (async) · /v1/image-to-video (sync)
Pricing:
  • 1280×720 — $0.04/sec
  • 1920×1080 — $0.08/sec
  • 2560×1440 — $0.16/sec
  • 3840×2160 — $0.32/sec
Notes:
  • Uses the Pro rendering path for maximum fidelity.
  • Ideal when visual consistency is critical.

Image-to-Video

LTX-2.3
Fast

Designed for quick iteration, previews, and fast creative exploration.

URL path:
/v2/image-to-video (async) · /v1/image-to-video (sync)
Pricing:
  • 1280×720 — $0.03/sec
  • 1920×1080 — $0.06/sec
  • 2560×1440 — $0.12/sec
  • 3840×2160 — $0.24/sec
Notes:
  • Same compute cost as Text-to-Video Fast.
  • Resolution and duration determine total cost.

Image-to-Video

LTX-2.5
Fast

Designed for quick iteration, previews, and fast creative exploration.

URL path:
/v2/image-to-video (async) · /v1/image-to-video (sync)
Pricing:
  • 1280×720 — $0.09/sec
  • 1920×1080 — $0.13/sec
  • 2560×1440 — $0.19/sec
  • 3840×2160 — $0.30/sec
Notes:
  • Same compute cost as Text-to-Video Fast.
  • Resolution and duration determine total cost.

Image-to-Video

LTX-2.5
Pro

For detailed, stable motion derived from a still image. Best for high-quality sequences, storytelling, and production use.

URL path:
/v2/image-to-video (async) · /v1/image-to-video (sync)
Pricing:
  • 1280×720 — $0.12/sec
  • 1920×1080 — $0.17/sec
  • 2560×1440 — $0.25/sec
  • 3840×2160 — $0.39/sec
Notes:
  • Uses the Pro rendering path for maximum fidelity.
  • Ideal when visual consistency is critical.

Retake - Video Editing

LTX-2.3
Pro

Refine only the parts that need adjustment - no need to regenerate the whole video. Perfect for fixing scenes, adjusting elements, or improving localized areas.

URL path:
/v2/retake (async) · /v1/retake (sync)
Pricing:
  • 1920×1080 — $0.10/sec
Notes:
  • Currently available in 1080p only.
  • Billed per second of input video.

Audio to Video (A2V)

LTX-2.3
Pro

Generate video directly from audio — where voice, music, and sound define structure, pacing, and motion.

URL path:
/v2/audio-to-video (async) · /v1/audio-to-video (sync)
Pricing:
  • 1280×720 — $0.06/sec
  • 1920×1080 — $0.10/sec
  • 2560×1440 — $0.18/sec
  • 3840×2160 — $0.34/sec
Supported inputs:
  • Audio: WAV, MP3, M4A, OGG
  • Image (optional): PNG, JPEG, WEBP
Notes:
  • Billed per second of input audio.
  • Generates up to ~20 seconds per request.
  • Full-length videos can be created by chaining multiple requests.

Audio to Video (A2V)

LTX-2.5
Fast

Generate video directly from audio — where voice, music, and sound define structure, pacing, and motion.

URL path:
/v2/audio-to-video (async) · /v1/audio-to-video (sync)
Pricing:
  • 1280×720 — $0.09/sec
  • 1920×1080 — $0.13/sec
  • 2560×1440 — $0.19/sec
  • 3840×2160 — $0.30/sec
Supported inputs:
  • Audio: WAV, MP3, M4A, OGG
  • Image (optional): PNG, JPEG, WEBP
Notes:
  • Billed per second of input audio.
  • Generates up to ~20 seconds per request.
  • Full-length videos can be created by chaining multiple requests.

Audio to Video (A2V)

LTX-2.5
Pro

Generate video directly from audio — where voice, music, and sound define structure, pacing, and motion.

URL path:
/v2/audio-to-video (async) · /v1/audio-to-video (sync)
Pricing:
  • 1280×720 — $0.12/sec
  • 1920×1080 — $0.17/sec
  • 2560×1440 — $0.25/sec
  • 3840×2160 — $0.39/sec
Supported inputs:
  • Audio: WAV, MP3, M4A, OGG
  • Image (optional): PNG, JPEG, WEBP
Notes:
  • Billed per second of input audio.
  • Generates up to ~20 seconds per request.
  • Full-length videos can be created by chaining multiple requests.

Beta - HDR Video Generation

LTX-2.3
Pro

Convert SDR video to 16-bit HDR for greater dynamic range and post-production flexibility — built for professional grading and finishing workflows.

URL path:
/v2/video-to-video-hdr
Pricing:
  • Up to 1080p (≤ 1920×1080 pixels) — $0.20/sec
  • Up to 1440p (≤ 2560×1440 pixels) — $0.40/sec
  • Up to 4K (≤ 3840×2160 pixels) — $0.80/sec
Notes:
  • Video-to-video only (SDR → HDR)
  • Output delivered as per-frame 16-bit EXR (ZIP)
  • Billed per second of input video
  • Max duration depends on resolution tier (up to ~7s at 1080p, up to ~4s at 2560×1440p)

Extend

LTX-2.3
Pro

Extend a video by generating additional frames at the beginning or end.

URL path:
/v2/extend (async) · /v1/extend (sync)
Pricing:
  • 1920×1080 — $0.10/sec
Notes:
  • Billed frames = extended portion + context frames from input video, capped at 505 total.
  • Billed seconds depend on the input video’s frame rate (~21 seconds at 24fps).
  • Full-length videos can be created by chaining multiple requests.
  • Currently available in 1080p only.

Reframe

LTX-2.3
Pro

Expand a video to any aspect ratio without cropping, while preserving the original frame, motion, and quality.

URL path:
/v2/video-to-video-reframe
Pricing:
  • 720p output — $0.10/sec
  • 1080p output — $0.20/sec
Notes:
  • Supports aspect ratio expansion including 16:9, 9:16, 1:1, 4:5, and more.
  • Supports videos up to 60 seconds.
  • Built on LTX-2.3

‍

//

FAQs

How is video generation priced in the LTX API?

Video generation in the LTX API is billed per second — there are no request fees or per-asset charges. Your rate depends on the endpoint, the model variant, and the output resolution.

Text-to-Video and Image-to-Video are billed on the duration of the generated video. Audio-to-Video is billed on the input audio. Retake, Extend, HDR Upscale, and Reframe are billed on the input video.

Current LTX-2.5 rates per second:

  • ltx-2-5-fast — 720p $0.09 · 1080p $0.13 · 1440p $0.19 · 4K $0.30
  • ltx-2-5-pro — 720p $0.12 · 1080p $0.17 · 1440p $0.25 · 4K $0.39

Portrait and landscape are priced identically at the same resolution tier.

What factors affect the cost of video generation?

The cost of video generation is determined by:

  • Billed duration — the generated video on Text-to-Video and Image-to-Video; the input audio or input video on the other endpoints
  • Output resolution — 720p, 1080p, 1440p, or 4K
  • Model variant — ltx-2-5-fast, ltx-2-5-pro, ltx-2-3-fast, or ltx-2-3-pro
  • Endpoint — HDR Upscale and Reframe have their own rate tiers

Higher resolutions and Pro variants have higher per-second costs.

How is pricing calculated for Text-to-Video and Image-to-Video?

Text-to-Video and Image-to-Video use the same per-second rate at every resolution, billed on the duration of the generated video.

With automatic duration, you are charged for the length the model actually produces. On prepaid accounts, credits are held against the longest duration your resolution and frame rate allow, and the unused remainder is released when the job finishes.

How is Retake (video editing) priced?

Retake requires ltx-2-3-pro and is billed at $0.10 per second of the input video you upload, at 1080p.

What is the difference between the Fast and Pro model variants?

Fast is optimized for speed and cost — best for iteration, previews, and high-volume generation.

Pro is optimized for visual fidelity and motion stability, for final and commercial-grade renders. On LTX-2.5, both variants support 720p through 4K.

On LTX-2.3, Pro is also required for Audio-to-Video, Retake, Extend, and Reframe.