# Genmo Mochi Pipeline (Self-Hosted OSS)

**Canonical:** https://apis.io/apis/genmo-ai/genmo-ai-mochi-pipeline-api/  
**Provider:** Genmo — https://apis.io/providers/genmo-ai/  
**Documentation:** https://github.com/genmoai/mochi

Genmo Mochi Pipeline (Self-Hosted OSS) is one of 3 APIs that [Genmo](https://apis.io/providers/genmo-ai/) publishes on the [APIs.io](https://apis.io/) network. Tagged areas include Video Generation, Text-to-Video, Open-Source, and Self-Hosted. The published artifact set on APIs.io includes API documentation and an engineering blog.

The first-party access surface is the open-source model itself. The Mochi repo (Apache-2.0) ships a "simple composable API" in Python - MochiSingleGPUPipeline built from T5ModelFactory, DitModelFactory, and DecoderModelFactory - invoked with prompt, resolution, num_frames, inference steps, guidance scale, and seed to generate 480p video locally. It also provides a cli.py, a Gradio UI (gradio_ui.py), and native ComfyUI support. This is a code library / local inference pipeline, not a hosted network API; weights (~60GB VRAM) are downloaded from Hugging Face. There is no Genmo REST endpoint - self-host it or use a partner (see the Replicate and fal.ai entries).

## Machine-readable artifacts (3)

- **Documentation** — https://github.com/genmoai/mochi
- **SourceCode** — https://huggingface.co/genmo/mochi-1-preview
- **Blog** — https://www.genmo.ai/blog/mochi-1-a-new-sota-in-open-text-to-video

## Other Genmo APIs (2)

- [Mochi 1 on Replicate (Third-Party Hosted)](https://apis.io/apis/genmo-ai/genmo-ai-mochi-replicate-api/)
- [Mochi v1 on fal.ai (Third-Party Hosted)](https://apis.io/apis/genmo-ai/genmo-ai-mochi-fal-api/)

## Tags

Video Generation, Text-to-Video, Open-Source, Self-Hosted

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/apis/genmo-ai/genmo-ai-mochi-pipeline-api/). The API's provider profile, Kin Score and agent-readiness rating are at https://apis.io/providers/genmo-ai/.