MOSS-Audio 4B Thinking on Hugging Face Inference Endpoints

Name: MOSS-Audio 4B Thinking on Hugging Face Inference Endpoints
Brand: MOSI AI
SKU: moss-audio-4b-thinking-huggingface-inference

MOSS-Audio · MOSI AI

Open Source

Last refreshed 2026-06-29. 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.

Input / 1M

Output / 1M

Cache

Not sourced

Batch

Not sourced

Setup recipe

Docs fallback

Install

Use the provider REST API or SDK

Auth

Create a provider API key

Call

model: OpenMOSS-Team/MOSS-Audio-4B-Thinking

Model ID

OpenMOSS-Team/MOSS-Audio-4B-Thinking

Request example

Curated snippets for this provider are not sourced yet. Use Hugging Face Inference Endpoints documentation with model ID 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

MultimodalReasoningAudio

About MOSS-Audio 4B Thinking

MOSS-Audio 4B Thinking is the reasoning-tuned 4.6B variant of MOSI AI 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.

Get Started

Model Card Docs Portal Playground Pricing

Model Specs

Released2026-04-13

Parameters4.6B

ArchitectureAudio / Speech

Related Models on Hugging Face Inference Endpoints

MOSS-Audio 4B Instruct MOSS-Audio 8B Instruct MOSS-Audio 8B Thinking

Provider

Hugging Face Inference Endpoints

Hugging Face

All models on Hugging Face Inference Endpoints →Provider setup guide →