Using MOSS-Image Base on MOSI API Platform

Implementation guide · MOSS-Image · MOSI AI

Serverless
Open Source

MOSI API Platform exposes MOSS-Image Base through model ID moss-image-base-1.0. Use the setup steps, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-10-22. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at MOSI API Platform and generate an API key.
  2. 2
    Use the MOSI API Platform SDK or REST API to call moss-image-base-1.0 — see the documentation for request format.
API PortalDocumentationPricingModel Card

Code Examples

See MOSI API Platform documentation for integration details.

Capabilities

VisionMultimodal

About MOSS-Image Base

MOSS-Image Base is the open 5B diffusion-transformer text-to-image base model from the OpenMOSS team at MOSI AI. It takes natural-language prompts of up to 4K tokens, tag sequences or JSON layouts that place text and objects, renders Chinese and English text, and is meant as a foundation for fine-tuning. Apache 2.0.

Full model details →

Model Specs

Released2026-10-16
Parameters5B
ArchitectureDiffusion Transformer

More Models on MOSI API Platform

MOSS-Image SFT
All models on MOSI API Platform →

Provider

MOSI API Platform

MOSI AI