Model library

Browse our library of open source models that are ready to deploy behind an API endpoint in seconds.

Deploy your own model

15 transcription models

Transcription

MOSS Transcribe Diarize

MOSS Transcribe Diarize - H100

Transcription

Whisper Large V3 Turbo

V3 - Turbo - RTX-PRO-6000

Transcription

Whisper Large V3

V3 - RTX-PRO-6000

Transcription

Whisper Large V3 (Streaming)

V3 - RTX-PRO-6000

Transcription

NVIDIA Nemotron 3.5 ASR (Multilingual)

Nemotron 3.5 ASR - H100

Transcription

NVIDIA Nemotron 3 ASR (English)

Nemotron 3 ASR - H100

Transcription

Voxtral Mini 4B Realtime 2602

2602 - Mini - H100 MIG 40GB

Transcription

Ultravox v0.6 70B

v0.6 - H100

Transcription

Parakeet TDT 0.6B V3

Parakeet TDT 0.6B V3 - V3

Transcription

Qwen3 ASR 1.7B Streaming

Qwen3 ASR 1.7B - Streaming - RTX-PRO-6000

Transcription

Qwen 3 ASR 1.7B

RTX-PRO-6000

Transcription

Whisper Large V3 Turbo (Streaming)

V3 - Turbo - RTX-PRO-6000

Transcription

Voxtral Mini 3B

2507 - Mini - H100 MIG 40GB

Partner Model

Transcription

Ink 2.0

Transcription

Voxtral Small 24B

2507 - Small - H100

🔥 Trending models

Model API

LLM

GLM-5.3

5.3

Model API

LLM

GLM-5.3-Flash

5.3 - Flash

Model API

LLM

DeepSeek V4 Pro 0813

V4 - Pro 0813

Model API

LLM

Kimi K3

Explore Baseten today

Start deploying Talk to an engineer