> ## Documentation Index
> Fetch the complete documentation index at: https://docs.infery.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Five minutes from sign-up to your first chat response and first API call.

## 1. Create an account

Sign up at **[app.infery.ai/register](https://app.infery.ai/register)**.
Free accounts get **50 trial credits** immediately — enough to try chat, a few
images and some voice.

## 2. Open the Playground

Once you're in, the **Playground** is the first screen you see.

* Type a prompt in the input at the bottom, pick a model (default: auto-routed) and press Enter.
* Switch between **Chat · Generate Image · Text to Speech · Speech to Text · Generate Video · Generate Music** at the top.
* Drop a PDF, image or audio file on the message box to attach it.

<Tip>
  Your first chat becomes a `Chat`. Create a `Project` to group related chats and share settings. See [Chats and Projects](/playground/chats-and-projects).
</Tip>

## 3. Create an API key

Go to **Settings → API Keys** and click **Create key**. Give it a name
("Production", "Local dev"), copy the plaintext key — it's only shown once.

API keys look like:

```
inf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
```

<Warning>
  Treat API keys as secrets. Never commit them to git. Revoke a key immediately if exposed — it takes \~5 seconds in the dashboard.
</Warning>

## 4. Make your first API call

Our gateway is OpenAI-compatible. Point the OpenAI SDK at `https://api.infery.ai`:

<CodeGroup>
  ```bash curl theme={null}
  curl https://api.infery.ai/v1/chat/completions \
    -H "Authorization: Bearer $INFERY_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "gpt-4o",
      "messages": [{"role": "user", "content": "Say hello in Russian"}]
    }'
  ```

  ```python python theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key=os.environ["INFERY_API_KEY"],
      base_url="https://api.infery.ai/v1",
  )

  resp = client.chat.completions.create(
      model="gpt-4o",
      messages=[{"role": "user", "content": "Say hello in Russian"}],
  )
  print(resp.choices[0].message.content)
  ```

  ```typescript node theme={null}
  import OpenAI from 'openai';

  const client = new OpenAI({
    apiKey: process.env.INFERY_API_KEY,
    baseURL: 'https://api.infery.ai/v1',
  });

  const resp = await client.chat.completions.create({
    model: 'gpt-4o',
    messages: [{ role: 'user', content: 'Say hello in Russian' }],
  });
  console.log(resp.choices[0].message.content);
  ```
</CodeGroup>

You'll get back a standard OpenAI-format response. The cost in credits is
returned as an extra header (`x-credits-used`) and inside the final SSE chunk
when streaming.

## 5. Explore

<CardGroup cols={2}>
  <Card title="Add teammates" href="/workspaces/members-and-roles">
    Invite, assign roles, keep billing people out of your playground.
  </Card>

  <Card title="Set a budget" href="/workspaces/budget-alerts">
    Get notified at 50/75/90% of your monthly plan.
  </Card>

  <Card title="Upload reusable files" href="/api-reference/files">
    `POST /v1/files` once, reference them by `file_id` forever.
  </Card>

  <Card title="Set up fallbacks" href="/workspaces/fallback-chains">
    Route to a backup model automatically when the primary rate-limits.
  </Card>
</CardGroup>