Getting Started

<h2 id="installation">Installation</h2>
<p>This is easy, just get our <code>deepctl</code> command line tool installed on your machine.
Here is how to run it:</p>
<pre><code class="language-bash">curl https://deepinfra.com/get.sh | sh
</code></pre>
<p>Make sure all is well by running:</p>
<pre><code class="language-bash">deepctl --version
</code></pre>
<p>Login to DeepInfra (using your GitHub account)</p>
<pre><code class="language-bash">deepctl login
</code></pre>
<p>This will take you to the browser to login in DeepInfra using your GitHub account.
When you are done, come back to the terminal.</p>
<h2 id="deployment">Deployment</h2>
<p>Now lets actually deploy some models to production and use them for inference. It is really easy.</p>
<pre><code class="language-bash">deepctl deploy create -m openai/whisper-small
</code></pre>
<p>This will deploy the <code>whisper-small</code> model from the <code>openai</code> organization to production.
It only takes a few seconds to deploy and now you are ready to use it for inference.</p>
<h2 id="inference">Inference</h2>
<p>Once a model is deployed on DeepInfra, you can use it with either our rest API or our deepctl
command line too. Here is how to use it with the command line tool:</p>
<pre><code class="language-bash">deepctl infer -m openai/whisper-small -i audio=@/path/to/audio.mp3
</code></pre>