LLM Reference
Hugging Face Inference Endpoints

Using MOSS-Audio 4B Instruct on Hugging Face Inference Endpoints

Implementation guide · MOSS-Audio · MOSI AI

Open Source

Hugging Face Inference Endpoints exposes MOSS-Audio 4B Instruct through model ID OpenMOSS-Team/MOSS-Audio-4B-Instruct. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-29. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Hugging Face Inference Endpoints and generate an API key.
  2. 2
    Use the Hugging Face Inference Endpoints SDK or REST API to call OpenMOSS-Team/MOSS-Audio-4B-Instruct — see the documentation for request format.
API PortalDocumentationPricingModel Card

Code Examples

See Hugging Face Inference Endpoints documentation for integration details.

Pricing on Hugging Face Inference Endpoints

Capabilities

MultimodalAudio

About MOSS-Audio 4B Instruct

MOSS-Audio 4B Instruct is the instruction-following 4.6B variant of MOSI AI and OpenMOSS Team's open-weight audio understanding model. It combines a MOSS-Audio encoder with a Qwen3-4B language backbone for speech, environmental sound, music, captioning, time-aware question answering, timestamped ASR, and audio-grounded reasoning.

Full model details →

Model Specs

Released2026-04-13
Parameters4.6B
ArchitectureAudio / Speech

More Models on Hugging Face Inference Endpoints

MOSS-Audio 4B ThinkingMOSS-Audio 8B InstructMOSS-Audio 8B Thinking
All models on Hugging Face Inference Endpoints →

Provider

Hugging Face Inference Endpoints
Hugging Face Inference Endpoints

Hugging Face

New York City, New York, United States