whatmodel.sh / video / PixVerse 5.5

PixVerse 5.5

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

PixVerse 5.5 is a closed-weights video model from PixVerse, released December 2025.

Model information sources

Release date ↗

51.6±10.0#49 of 93 video modelsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The video models ranked either side of PixVerse 5.5, out of 139 with a score, then more from PixVerse.

#modelscorewhereRAMreleased
59HunyuanVideo 1.5 Tencent52±2api $0.075/sec +local~20GB2025-11
60Cosmos3-Nano NVIDIA52±3local~42GB2026-05
61PixVerse 5.5 PixVerse52±10api $0.060/sec2025-12
62Kling 1.6 (Pro mode) Kuaishou (Kling AI)52±4comparison only2024-12
63LongCat-Video Meituan51±2api $0.040/sec +local~100GB2025-10
more from PixVerse
35PixVerse V5.6 PixVerse59±2api $0.045/sec2026-02

see all video models · find the ones that fit your machine

$ what it's good at

text to video▆▄▃▄▆▅█▃▂▂▂▄ #31 of 68 * · 57% of its score · 1 test

Beats Kling 2.1 Master here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
HumanScore (T2V)85.5% ✎▂··▂··█▄▂··▆ beats 3/11easy · avg 84%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 57%blunt

$ where to run it

Through an API

api · $0.060/sec · docs.platform.pixverse.ai ↗ · price sourceUSD per second of generated video, 720p, 5-second single clip, no audio. Product: PixVerse platform API text-to-video / image-to-video. API model: V5.5. Price basis: 60 credits per 5-s 720p clip × $0.005 per credit (pay-as-you-go credit purchase: $10 = 2,000 credits) ÷ 5 s. With audio: 70 credits per 5-s clip; multi-clip modes, 8-s and 10-s clips and membership credit rates differ. Currency: USD. PixVerse platform model pricing page, observed 2026-09-25.

$ how the score was worked out · HumanScore: Benchmarking Huma… 57%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
HumanScore: Benchmarking Human Motions in Generated Videos1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 57%CC-BY-4.0
prior · pull toward the middle▇▇▇▇▇▇▇▇▇▇▇▇▇ 43%
weighted average= 51.6

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json