OpenAI logoOpenAI

OpenAI — while best known for ChatGPT — has created dozens of models and open sourced many of them, most notably Whisper.

OpenAI models

OpenAI logoWhisper (best performance)

Audio transcription
V3H100 MIG 40GB

OpenAI logoWhisper V3

Audio transcription
V3H100 MIG 40GB

OpenAI logoCLIP

Image classification
A10G

OpenAI logoWhisper V3 Turbo

Audio transcription
V3TurboH100 MIG 40GB

About OpenAI

OpenAI is a research organization creating generative AI models founded in 2015 and headquartered in San Francisco. While OpenAI’s most famous models — such as GPT-3.5, GPT-4, and DALLE 3 — are proprietary and closed source, the company has released several open source models, most notably the Whisper model family for audio transcription.

Use open source models with ChatCompletions API

If you're interested in experimenting with open source alternatives to models like GPT-3.5 but don't want to make major code changes, Baseten supports an OpenAI ChatCompletions-compatible endpoint for certain LLMs in the model library, including:

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.

$

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