We raised a $75m series C to build the future of inference

Model library

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

Deploy your own model

LLM Audio transcription Text to speech Image generation Audio generation Text embeddings Image to video Image classification Image processing

large language models

Deploy Llama 3.3 Nemotron 49B Super - NVIDIA NIM on Baseten

Llama 3.3 Nemotron 49B Super - NVIDIA NIM

LLM

3.3NemotronH100

Mistral Small 3.1

LLM

3.1vLLMH100

Gemma 3 27B IT

LLM

3InstructvLLMH100

DeepSeek-R1 Llama 70B

LLM

R1LlamaTRT-LLMH100

Llama 3.3 70B Instruct

LLM

3.3TRT-LLMH100

DeepSeek-R1 Qwen 32B

LLM

R1QwenTRT-LLMH100

audio transcription models

Whisper (best performance)

Audio transcription

V3H100 MIG 40GB

Whisper V3

Audio transcription

V3H100 MIG 40GB

Whisper V3 Turbo

Audio transcription

V3TurboH100 MIG 40GB

image generation models

Prompt: A movie still of an astronaut with a dark visor with a lightning bolt superhero icon on his chest

SDXL Lightning

Image generation

1.0LightningA100

moss covered astronaut

Stable Diffusion 3 Medium

Image generation

3A100

Stable Diffusion XL

Image generation

XL 1.0A10G

flux-dev

Image generation

devbloat16H100 MIG 40GB

flux-schnell

Image generation

schnellbfloat16H100 MIG 40GB

Comfy UI

Image generation

A10G

text embeddings models

Prompt: A movie still of a squirrel in a forest green ski suit

Nomic Embed v1.5

Text embeddings

v1.5T4

All MPNet Base V2

Text embeddings

v2CPU

All MiniLM L6 v2

Text embeddings

v2CPU

Jina Embeddings V2 Base EN

Text embeddings

V2ENCPU

audio generation models

Prompt: a cyberpunk movie still of a robot DJ at a club. Model: Playground 2.

AudioGen Medium

Audio generation

A10G

MusicGen Melody

Audio generation

MelodyA10G

MusicGen Large

Audio generation

MusicA10G

Meta models

Llama 3.3 70B Instruct

LLM

3.3TRT-LLMH100

Llama 3.1 8B Instruct

LLM

3.1InstructTRT-LLMH100

Llama 3.1 405B Instruct

LLM

3.1InstructH100

Llama 11B Vision

Llama 3.2 11B Vision Instruct

LLM

3.2VisionA100

Llama 3.1 70B Instruct

LLM

3.1InstructTRT-LLMH100

Llama 3.2 90B Vision Instruct

LLM

3.2VisionH100

Stability AI models

moss covered astronaut

Stable Diffusion 3 Medium

Image generation

3A100

Stable Diffusion XL

Image generation

XL 1.0A10G

Stable Video Diffusion

Image to video

Video 1.0A100

Comfy UI

Image generation

A10G

SDXL ControlNet Canny

Image generation

XL 1.0ControlNet - CannyA10G

SDXL ControlNet Depth

Image generation

XL 1.0ControlNet - DepthA10G

Mistral AI models

Mistral Small 3.1

LLM

3.1vLLMH100

Pixtral 12B

LLM

PixtralvLLMH100

Mistral 7B Instruct

LLM

v3TRT-LLMH100 MIG 40GB

Mixtral 8x7B Instruct

LLM

v1TRT-LLMH100

Sail

Mixtral 8x22B

LLM

H100

Deploy any model in just a few commands

Avoid getting tangled in complex deployment processes. Deploy best-in-class open-source models and take advantage of optimized serving for your own models.

Start deploying

$

truss init -- example stable-diffusion-2-1-base ./my-sd-truss

$

cd ./my-sd-truss

$

export BASETEN_API_KEY=MdNmOCXc.YBtEZD0WFOYKso2A6NEQkRqTe

$

truss push

INFO

Serializing Stable Diffusion 2.1 truss.

INFO

Making contact with Baseten 👋 👽

INFO

🚀 Uploading model to Baseten 🚀

Upload progress: 0% | | 0.00G/2.39G