MOSS-Audio 4B Thinking on Hugging Face Inference Endpoints
MOSS-Audio · MOSI Intelligence
Last refreshed 2026-06-04. Next refresh: weekly.
Why use MOSS-Audio 4B Thinking on Hugging Face Inference Endpoints?
Hugging Face Inference Endpoints offers MOSS-Audio 4B Thinking with competitive pricing. Hugging Face is a leading AI community and platform dedicated to democratizing artificial intelligence.
Setup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: OpenMOSS-Team/MOSS-Audio-4B-ThinkingOpenMOSS-Team/MOSS-Audio-4B-ThinkingRequest example
OpenMOSS-Team/MOSS-Audio-4B-Thinking.Gotchas
- Use provider model ID "OpenMOSS-Team/MOSS-Audio-4B-Thinking", not the LLMReference slug "moss-audio-4b-thinking".
Capabilities
About MOSS-Audio 4B Thinking
MOSS-Audio 4B Thinking is the reasoning-tuned 4.6B variant of MOSI Intelligence and OpenMOSS Team's open-weight audio understanding model. It uses the MOSS-Audio encoder and Qwen3-4B backbone, adding chain-of-thought-oriented post-training for stronger complex audio reasoning while retaining speech, sound, music, timestamp, captioning, and QA coverage.
FAQ
What API model ID do I use for MOSS-Audio 4B Thinking on Hugging Face Inference Endpoints?
Use the model ID OpenMOSS-Team/MOSS-Audio-4B-Thinking when calling Hugging Face Inference Endpoints's API.
Who created MOSS-Audio 4B Thinking?
MOSS-Audio 4B Thinking was created by MOSI Intelligence as part of the MOSS-Audio model family.
Is MOSS-Audio 4B Thinking open source?
MOSS-Audio 4B Thinking is open source under Apache 2.0 according to the seed data.