Skip to main content

Direct comparison

LTX-2 19B vs. Pika 2.2

Compare the exact model versions across shared blind-preference benchmarks, public pricing, release dates, resolution, duration, native audio, access, and model availability.

Overview

Technical specifications and pricing

Technical limits come from model or API documentation. A representative minute price appears only when it can be traced to the exact model. Different resolutions and audio settings may still affect the final charge.

Specifications and pricing for LTX-2 19B and Pika 2.2
AttributeLTX-2 19BPika 2.2
ProviderLightricksPika
ReleasedOctober 2025February 2025
AccessAPI, Web app, LocalAPI, Web app
WeightsOpen weightsProprietary
Parameters19 billionNot published
Maximum resolutionNot publishedNot published
Maximum durationNot publishedNot published
Native audioYesNot published
Representative API priceNot publishedNot published
LifecycleNo separate noticeNo separate notice
Technical sourceModel sourceVerified 2026-08-24Model sourceVerified 2026-08-24

Performance

Shared video benchmarks

A row appears only when both exact model versions occur in the same LMArena task and stored dataset revision. Text-to-video and image-to-video are never merged into one score.

LTX-2 19BPika 2.2
LMArena Text to VideoBlind preference rating from the same task and dataset revision
LTX-2 19BHigher value1,151.1
Pika 2.21,007.7
LMArena Image to VideoBlind preference rating from the same task and dataset revision
LTX-2 19BHigher value1,154
Pika 2.2995.9

Key to the marks:better valuebetter, but not conclusivetie

Shared video benchmarks for LTX-2 19B and Pika 2.2
BenchmarkLTX-2 19BPika 2.2Source
LMArena Text to Video
Higher rating1,151.1Rank 38, 95% interval 1,142.8 to 1,159.5, 64,706 votes
1,007.7Rank 44, 95% interval 992.4 to 1,023, 5,746 votes
LMArenaRetrieved 2026-08-26
LMArena Image to Video
Higher rating1,154Rank 42, 95% interval 1,148.7 to 1,159.2, 223,241 votes
995.9Rank 45, 95% interval 982.4 to 1,009.5, 8,665 votes
LMArenaRetrieved 2026-08-26

Higher rating is better. A clear lead is shown only when the published 95% intervals do not overlap.

Key to the marks:better valuebetter, but not conclusivetie

Visual comparison

Sample videos

Only runs from both exact model versions under the same archived prompt and first-output rule appear here. Provider showcases and substitute versions remain excluded.

Controlled practical comparison. Both exact model versions received the same archived prompt in one request. The first output counts. Playback uses the first five seconds, 1280 × 720 pixels, 30 fps, no crop, and muted audio. Provider-side randomness and prompt processing remain model characteristics.

Motion and physical consistency

Anatomy, object consistency, camera tracking, rain, and reflections

LTX-2 19B

Run details

fal.ai. fal-ai/ltx-2-19b/text-to-video. 16:9, one request, first output, requested 5 s, seed 1843750023, request {"prompt":"Generate exactly one continuous five-second 16:9 cinematic video. A fictional bicycle courier in a mustard-yellow raincoat rides a red city bicycle from left to right across a rain-wet Hamburg street at blue hour for the entire clip. The camera tracks her smoothly at waist height. Both hands remain visible on the handlebars, the bicycle geometry stays physically correct, and a transparent umbrella fixed to the bicycle moves naturally in the wind. Wet-street reflections and raindrops follow realistic physics. No cuts, no slow motion, no text, no logos, no subtitles, and no audio.","video_size":"landscape_16_9","num_frames":121,"fps":24,"generate_audio":false,"use_multiscale":true,"camera_lora":"none","acceleration":"regular","guidance_scale":3,"num_inference_steps":40,"enable_prompt_expansion":false,"enable_safety_checker":true,"video_output_type":"X264 (.mp4)","video_quality":"high","video_write_mode":"balanced"}, configured price estimate $0.25.

Generated Aug 24, 2026. Source

Pika 2.2

Run details

fal.ai. fal-ai/pika/v2.2/text-to-video. 16:9, one request, first output, requested 5 s, seed provider random, request {"prompt":"Generate exactly one continuous five-second 16:9 cinematic video. A fictional bicycle courier in a mustard-yellow raincoat rides a red city bicycle from left to right across a rain-wet Hamburg street at blue hour for the entire clip. The camera tracks her smoothly at waist height. Both hands remain visible on the handlebars, the bicycle geometry stays physically correct, and a transparent umbrella fixed to the bicycle moves naturally in the wind. Wet-street reflections and raindrops follow realistic physics. No cuts, no slow motion, no text, no logos, no subtitles, and no audio.","aspect_ratio":"16:9","resolution":"720p","duration":5}, configured price estimate $0.20.

Generated Aug 24, 2026. Source

Prompt and integrity hashes

Generate exactly one continuous five-second 16:9 cinematic video. A fictional bicycle courier in a mustard-yellow raincoat rides a red city bicycle from left to right across a rain-wet Hamburg street at blue hour for the entire clip. The camera tracks her smoothly at waist height. Both hands remain visible on the handlebars, the bicycle geometry stays physically correct, and a transparent umbrella fixed to the bicycle moves naturally in the wind. Wet-street reflections and raindrops follow realistic physics. No cuts, no slow motion, no text, no logos, no subtitles, and no audio.

Prompt SHA 256: 206a9182584e93790fd6df608e8a2065fe2c8f747e85aeaaf4c8ea84040e6299

LTX-2 19B, Original SHA 256: 50e1b2b965e454d2b281c824e51c37f67e77180db2666fe867f468cdd1915dec

LTX-2 19B, Normalized SHA 256: 6e14e70363b037fb264d594ea3b9bf8af38d28b3e4f17bf1ed6c86be8ef22229

Pika 2.2, Original SHA 256: 6e559c3845b8d1cca1779f52f558e1455283bd73584f4c3869098006d80ace0e

Pika 2.2, Normalized SHA 256: 21bbf477684d886ab183062fd059fcc4d4acbc45f846496c998aea542ae0e8cb

How to read the data

Preference is not the same as production fit

A higher LMArena rating means that outputs from this exact configuration were preferred more often in blind comparisons.

Motion control, identity consistency, audio, turnaround time, moderation, and licensing may matter more than the aggregate preference rating.

Prices are representative public minute rates, not a normalized cost benchmark.

More matchups

Compare LTX-2 19B and Pika 2.2 with other important video models using the same benchmark logic.

View the complete video model comparison