# Quickstart (/docs/quickstart)

Create an API key, add credit and make your first request.



<Steps>
  <Step>
    ### Sign in [#sign-in]

    Open the [console](https://console.cheapaimodel.ai) and sign in with Google.
  </Step>

  <Step>
    ### Add credit [#add-credit]

    Open the [Wallet](https://console.cheapaimodel.ai/wallet) page, pick an amount and pay with Stripe. The credit appears in your balance as soon as the payment clears.
  </Step>

  <Step>
    ### Create an API key [#create-an-api-key]

    Open the [API Keys](https://console.cheapaimodel.ai/keys) page and create a key. Copy the key (it starts with `sk-`) and keep it out of source control:

    ```bash title="Terminal"
    export CHEAPAIMODEL_API_KEY="sk-..."
    ```
  </Step>

  <Step>
    ### Make a request [#make-a-request]

    Pick a model ID from the [model catalog](/models) and send a chat completion. The examples use `deepseek-v4-1-flash`; replace it with any model you see in the catalog.

    <Tabs items="[&#x22;curl&#x22;, &#x22;Python&#x22;, &#x22;TypeScript&#x22;]">
      <Tab value="curl">
        ```bash
        curl https://api.cheapaimodel.ai/v1/chat/completions \
          -H "Authorization: Bearer $CHEAPAIMODEL_API_KEY" \
          -H "Content-Type: application/json" \
          -d '{
            "model": "deepseek-v4-1-flash",
            "messages": [{ "role": "user", "content": "Say hello in five words." }]
          }'
        ```
      </Tab>

      <Tab value="Python">
        ```python
        import os
        from openai import OpenAI

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

        completion = client.chat.completions.create(
            model="deepseek-v4-1-flash",
            messages=[{"role": "user", "content": "Say hello in five words."}],
        )
        print(completion.choices[0].message.content)
        ```
      </Tab>

      <Tab value="TypeScript">
        ```ts
        import OpenAI from "openai";

        const client = new OpenAI({
          baseURL: "https://api.cheapaimodel.ai/v1",
          apiKey: process.env.CHEAPAIMODEL_API_KEY,
        });

        const completion = await client.chat.completions.create({
          model: "deepseek-v4-1-flash",
          messages: [{ role: "user", content: "Say hello in five words." }],
        });
        console.log(completion.choices[0].message.content);
        ```
      </Tab>
    </Tabs>
  </Step>

  <Step>
    ### Check your usage [#check-your-usage]

    The console's [Overview](https://console.cheapaimodel.ai/overview), [Activity](https://console.cheapaimodel.ai/activity) and [Logs](https://console.cheapaimodel.ai/logs) pages show your balance, daily spend and every call with its token counts and cost.
  </Step>
</Steps>

## Next steps [#next-steps]

* Use a coding tool: [Codex CLI](/docs/guides/codex-cli), [Cursor](/docs/guides/cursor), [Cline](/docs/guides/cline), [Continue](/docs/guides/continue), [Zed](/docs/guides/zed) or [Aider](/docs/guides/aider).
* Build with a framework: [LangChain](/docs/guides/langchain), [LlamaIndex](/docs/guides/llamaindex), [Vercel AI SDK](/docs/guides/vercel-ai-sdk) or [LiteLLM](/docs/guides/litellm).
* Connect an app: [Open WebUI](/docs/guides/open-webui), [Dify](/docs/guides/dify), [n8n](/docs/guides/n8n) or [OpenClaw](/docs/guides/openclaw).
* Lock a key down with a budget or allowlist: [Authentication & API keys](/docs/concepts/authentication).