Last refreshed 2026-10-22. Next refresh: weekly.
Why use MOSS-Image SFT on MOSI API Platform?
MOSI API Platform offers MOSS-Image SFT. MOSI AI's first-party API platform for its MOSS models (MOSS-Image, MOSS-TTS, MOSS-VL).
Compare MOSS-Image SFT across 2 providers to find the best fit for your use caseInput / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: moss-image-sft-1.0Model ID
moss-image-sft-1.0Request example
Curated snippets for this provider are not sourced yet. Use MOSI API Platform documentation with model ID
moss-image-sft-1.0.Gotchas
- Use provider model ID "moss-image-sft-1.0", not the LLMReference slug "moss-image-sft".
Compare MOSS-Image SFT Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| fal API | — | — |
| MOSI API Platform | — | — |
Capabilities
VisionMultimodal
About MOSS-Image SFT
MOSS-Image SFT is the supervised fine-tuned release of MOSS-Image Base from the OpenMOSS team at MOSI AI. It keeps the 5B diffusion transformer and adds cleaner text grouping and layout for natural-language, tag or JSON-layout prompts, with Chinese and English text rendering. It is the checkpoint served on fal. Apache 2.0.
Get Started
Model Specs
Released2026-10-16
Parameters5B
ArchitectureDiffusion Transformer