Model profile

Mochi AI video generator

Genmo's open text-to-video model, a widely tracked open-source baseline for prompt adherence and motion quality.

Decision Snapshot

Score: 67

Score source: Mochi has reproducible open-weight evidence and community adoption; current frontier leaderboard data remains sparse.. Evidence confidence is high.

Best For

  • Open-Source Benchmarking
  • Local Text-To-Video
  • Community Fine-Tuning
  • Academic Tests

Supported Workflows

  • T2v
  • Open Weights
  • Lora

Access And Company

Built by Genmo. Public access is listed as Open Weights, Aggregator.

Entry Points

Score Breakdown

Weighted evidence dimensions separate model quality from access, web authority, ecosystem, and source confidence.

DimensionScoreWeightEvidenceConfidence
Model Quality Proxy 70 24% Mochi has reproducible open-weight evidence and community adoption; current frontier leaderboard data remains sparse. high
Missing: live Artificial Analysis rank/Elo by modality, live Arena AI rank/score by modality
Capability Depth 56 16% Supported workflow tags: t2v, open_weights, lora. Depth rewards T2V/I2V/V2V, references, native audio, editing, API, and open weights where present. medium
Missing: hands-on feature verification, mode-specific limits by duration/resolution
Access And Pricing 70 12% Access types: open_weights, aggregator. Pricing note: Open model; costs depend on self-hosting or third-party inference. Hosted services may charge per run. medium
Missing: current free tier, normalized price per video minute
Version Maturity 63 12% 2 version/history entries in the profile; latest public date is 2024-11-26. medium
Missing: automated release-note monitor, model ID/version mapping across providers
Ecosystem Popularity 100 10% GitHub snapshot includes 1 repo(s), 3,702 stars, 487 forks, 61 open issues, latest pushed 2025-11-14T01:17:56Z. high
Missing: Hugging Face downloads/likes, Replicate/fal usage/runs
Web Authority 28 10% SEO snapshot found product domain genmo.ai and company domain genmo.ai; sampled sitemap URL count is 0. medium
Missing: Similarweb/API traffic, Tranco rank
Company Distribution 62 10% Genmo distribution profile: Mochi matters most for users and developers who want an Apache 2.0 open-source text-to-video baseline and community fine-tuning rather than a polished consumer app alone.. medium
Missing: app store ratings/review volume, product MAU/traffic
Source Confidence 100 6% Profile source confidence is confirmed with 2 official URL(s), 3 feature evidence item(s), SEO present, GitHub present. high
Missing: paid/API evidence refresh, manual output review artifacts

What It Is

Primary content is rendered into static HTML.

Mochi is an open text-to-video model from Genmo. It is less of a polished consumer app than a foundation model and developer baseline, but it matters because it is open, benchmarkable, and community-extensible.

Mochi 1 was released as an open model under Apache 2.0, giving researchers and builders a comparatively permissive way to test, fine-tune, and integrate video generation. Its ecosystem includes GitHub, model cards, and community tools.

For consumers, Mochi is relevant when using hosted open-model services or local workflows. It should be scored separately from closed products because setup effort, generation speed, and output quality depend heavily on the runtime environment.

Key Features

  • Apache 2.0 open releaseThe Mochi repository describes an open-source video generation model from Genmo.Source
  • Text-to-video focusMochi focuses on high-quality text-to-video generation and prompt adherence.Source
  • LoRA/community workflowsMochi supports community experimentation and fine-tuning workflows.Source

Version Progress

  • 2024 / confirmed / confirmedMochi 1 previewOpen text-to-video model released by Genmo. Important open baseline for community benchmarks.

Latest News

Model-specific news entries link directly to the original publisher; article bodies stay off-site.

Limitations And Pricing

Open model; costs depend on self-hosting or third-party inference. Hosted services may charge per run.

  • Core Mochi 1 Is Not A Native Audio-Video Model.
  • Consumer Accessibility Requires A Wrapper Or Hosted Endpoint.