ChatGPT-web is a simple one-page web interface to the OpenAI ChatGPT API. To use it, you need to register for an OpenAI API key first. OpenAI bills per token (usage-based), which means it is a lot cheaper than ChatGPT Plus, unless you use more than 10 million tokens per month. All messages are stored in your browser's local storage, so everything is private. You can also close the browser tab and come back later to continue the conversation.

As an alternative to OpenAI, you can also use Petals swarm as a free API option for open chat models like Llama 2.

Set your OpenAI API key below:

{ if (event.target && event.target[0].value) { apiKeyStorage.set((event.target[0].value).trim()) } else { apiKeyStorage.set('') // remove api key } }} >

Save

{#if !apiKey}

Please enter your OpenAI API key above to use Open AI's ChatGPT API. At least one API must be enabled to use ChatGPT-web.

{/if}

Use Petals API and Models (Llama 2) {#if showPetalsSettings}

Set Petals API Endpoint:

{ if (event.target && event.target[0].value) { setGlobalSettingValueByKey('pedalsEndpoint', (event.target[0].value).trim()) } else { setGlobalSettingValueByKey('pedalsEndpoint', '') } }} >

Save

{#if !pedalsEndpoint}

Please only use the default public API for testing. It's best to configure a private endpoint and enter it above for connection to the Petals swarm.

{/if}

Petals lets you run large language models at home by connecting to a public swarm, BitTorrent-style, without hefty GPU requirements.

You are encouraged to set up a Petals server to share your GPU resources with the public swarm. Minimum requirements to contribute Llama 2 completions are a GTX 1080 8GB, but the larger/faster the better.

If you're receiving errors while using Petals, check swarm health and consider adding your GPU to the swarm to help.

Because Petals uses a public swarm, do not send sensitive information when using Petals.

{/if}