CherryVideo

Cherry LTX 2.3 Spicy API

Create 5, 10, or 15-second videos from a prompt or starting image with Cherry LTX 2.3 Spicy. Choose portrait or landscape in SD (640 × 960 or 960 × 640) or HD (896 × 1344 or 1344 × 896).
Text to videoImage to videoPortrait or landscape, SD and HD
Starting at
$0.006/ second
Try it in the PlaygroundLet an agent integrate this model

Input

async
Prompt
24 / 4,000 characters
Orientation
Output 640 × 960. Price depends only on SD or HD.
When you start from an image, it is center-cropped to fit the selected orientation.
Estimated run$0.03Current rate: $0.006 Per second of output

Output preview

This is a model capability preview. Sign in to submit a live request and inspect the generated result here.
videoSD5s640 × 960

Model information

Model ID
cherry/ltx2.3-spicy
Integration status
Inputs
Text prompt · optional starting image
Output
Generated video
Billing unit
Per second of output
Execution mode
Asynchronous. The request returns a generation ID; poll it or receive a webhook.
Available regions
China — Beijing
Last updated
Oct 1, 2026

Capabilities and limits

Resolutions
SD · HD
Duration
5–15s
Prompt limit
4,000 characters

Best for

Short scenesImage animationVisual concepts

Current customer pricing

For each Operation and price variant, the highest regional customer price is shown.
ModelCapabilityPrice variantCustomer price
Cherry LTX 2.3 Spicy · cherry/ltx2.3-spicyVideo generationHD$0.012 / second
Cherry LTX 2.3 Spicy · cherry/ltx2.3-spicyVideo generationSD$0.006 / second

Pricing and documentation

Cherry LTX 2.3 Spicy API pricingCompare variants and pricingMake an AI short dramaImage-to-video API documentation

Related guides

Cherry LTX 2.3 Spicy launch: September 25 price comparisonLTX 2.3 pricing: ModelRush Cherry vs the LTX API

Other recommended models

Reference-to-Video

Wan 2.7 R2V

Preserve a subject from image or video references in a new 2–10 second shot
Starting pricePricing pending
Text-to-Video

Wan 2.7 Text to Video

Turn a creative brief into a traceable asynchronous video job
Starting pricePricing pending
Text-to-VideoImage-to-VideoReference-to-Video
18+

Wan 3 Spicy

Create cinematic AI videos from text, images, or multimodal references
Starting pricePricing pending