MOSS-Audio 4B Instruct
Released
2026-04-13
Last refreshed
2026-10-07
Status
Researched 134d ago
Open sourceCommercial use: permittedMultimodalVisionMultimodal
MOSI AI releases · 7 in the last 12 months · this family litChangelog →
Specifications
- Family
- MOSS-Audio
- Released
- 2026-04-13
- Parameters
- 4.6B
- Architecture
- Audio / Speech
- Specialization
- audio-understanding
- Openness
- Open source
- License
- Apache 2.0OSI-approvedCommercial use: permitted
- Weights
- Available
- Code
- Unknown
- Training
- Pretrained
Pricing
Output / 1M
-
Input / 1M
-
Cheapest of 1 route · Hugging Face Inference Endpoints
Links
About
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.
Providers(1)
Compare API pricing across 1 tracked provider route for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Hugging Face Inference Endpoints | - | - | Partial |
Capabilities
MultimodalAudio
Benchmark peer barsfor Vision
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
Pricing
Output / 1M
-
Input / 1M
-
Cheapest of 1 route · Hugging Face Inference Endpoints
Links