> For the complete documentation index, see [llms.txt](https://infronai.gitbook.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://infronai.gitbook.io/docs/overview/quickstart.md).

# Quickstart

[Infron](https://infron.ai/) provides a **single API** that connects you to over thousands of **open-source models**, **commercial models**, and **search agents**—all powered by the Infron Open Model Protocol. 

As the world’s first ***AI Model Marketplace*** and ***Inference Provider Routing Platform***, Infron delivers cross-provider high availability, seamless developer workflows, and ultra-low-cost scalability through the Infron Routing Stack.

<table data-view="cards"><thead><tr><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><p><strong>Text Generation</strong><br></p><p>Generate and stream text with GPT-5.2, Claude Sonnet 4.6, Gemini 3 Flash, Llama 4, and 300+ more models.<br></p><p>AI SDK · OpenAI-compatible · Anthropic-compatible · OpenAI-Responses</p></td><td><a href="/pages/HYwJ9ECRWrwWZf9Iv4cb">/pages/HYwJ9ECRWrwWZf9Iv4cb</a></td></tr><tr><td><p><strong>Image Generation</strong><br></p><p>Create images from text prompts or edit existing images with Flux 2 Flex, Recraft V3, Imagen, and more.</p><p></p><p>AI SDK · OpenAI-compatible</p></td><td><a href="/pages/1bAdbFWqJy8GTNfKwF8p">/pages/1bAdbFWqJy8GTNfKwF8p</a></td></tr><tr><td><p><strong>Video Generation</strong><br></p><p>Create videos from text prompts, images, or video input with Veo 3.1, KlingAI, Wan, Grok Imagine Video, and more.</p></td><td><a href="/pages/CqjyssSCfkdus5B6pIcG">/pages/CqjyssSCfkdus5B6pIcG</a></td></tr><tr><td><p><strong>Audio Generation</strong><br></p><p>Create audio from text prompts, images, or video input with gpt-4o-mini-tts、tts-1, and more.</p></td><td><a href="/pages/cvdJ3cyZw0OlUuJzh4CZ">/pages/cvdJ3cyZw0OlUuJzh4CZ</a></td></tr><tr><td><p><strong>Search, Deepsearch &#x26; Extract</strong><br></p><p>generate search from text prompts with tavily, exa, jina, perpexity, and more.</p></td><td><a href="/pages/1fuCFLPtcMUjVcHlNnFR">/pages/1fuCFLPtcMUjVcHlNnFR</a></td></tr><tr><td><p><strong>Embedding &#x26; Reranker</strong><br></p><p>generate embedding and reranking from text prompts with gpt, qwen, and more.</p></td><td><a href="/pages/dPJ3lH8ZZVPUTMqlzPTQ">/pages/dPJ3lH8ZZVPUTMqlzPTQ</a></td></tr><tr><td><p><strong>Batch Generation</strong><br></p><p>Create batch completions from text prompts with AWS, Google, Azure, and more.</p></td><td><a href="/pages/sQF9BTt8eG2vZIQoEGf5">/pages/sQF9BTt8eG2vZIQoEGf5</a></td></tr></tbody></table>

### Quick Start Guide

Get up and running with Infron in under 5 minutes. Follow our step-by-step guide to set up your account and start calling ai models.

<details>

<summary><strong>Step 1：</strong><a href="https://infron.ai/login"><strong>Login to your account</strong></a> </summary>

Log in using your email or sign in with Google at <https://infron.ai/login>

<figure><img src="/files/hGCypO1fEdwLBMfZRFXi" alt=""><figcaption></figcaption></figure>

If you need more support or would like to talk to our experts, you can [book a meeting](https://infron.ai/contact) or join our [Discord](https://discord.com/invite/9WZfxfzjb8) or join our [X](https://x.com/BagelPayment).

</details>

<details>

<summary><strong>Step 2：</strong><a href="https://infron.ai/dashboard/apiKeys"><strong>Create your api key</strong></a> <strong>🔑</strong></summary>

API Keys are secret tokens used to authenticate your requests,they are unique to your account and should be kept confidential.

* **Navigate to the “**[**API Key**](https://infron.ai/dashboard/apiKeys)**” section.**

<figure><img src="/files/7xeFL8K4jU2bXZcBRebT" alt=""><figcaption></figcaption></figure>

* **Click on the "Add new key" button.**

<figure><img src="/files/XCYn6E215olZkfIeOciD" alt=""><figcaption></figcaption></figure>

* **Copy your API key and keep it safe.**

After that, feel free to explore our API reference for more details. Or to jump start into our first example below.

</details>

<details>

<summary><strong>Step 3：</strong><a href="https://infron.ai/dashboard/credits"><strong>Set up biling</strong></a> <strong>⏰</strong></summary>

Some features will only be available to you once you‘ve set up billing.

* **Navigate to the “**[**Billing**](https://infron.ai/dashboard/credits)**” section.**

<figure><img src="/files/gJACIlNdclFqHyeRIjML" alt=""><figcaption></figcaption></figure>

* Click "**Top up**".
* Enable "**Enable Auto Top Up**"
* Enable "[**Low Balance Alert**](https://infron.ai/dashboard/budgets-alerts)"

<figure><img src="/files/HCvBz6k7oY7VdO3mc2BO" alt=""><figcaption></figcaption></figure>

Get notified via email when your account balance drops below your configured threshold.

* Set "[**Budget Limit**](https://infron.ai/dashboard/budgets-alerts)".&#x20;

<figure><img src="/files/lI5hyRratJ5VZnxZA1Hj" alt=""><figcaption></figcaption></figure>

</details>

<details>

<summary><strong>Step 4：Make your first ai model call 💐</strong></summary>

* **For directly http integration**

Our HTTP API can be used with any programming language, e.g. Python, JavaScript, and other languages.

explore the [`LLM`](https://infron.ai/models?category=LLM), [`VLM`](https://infron.ai/models?category=LLM), [`Image Generation`](https://infron.ai/models?category=Text+to+Image), [`Video Generation`](https://infron.ai/models?category=Text+to+Video), [`Audio Generation`](https://infron.ai/models?category=Text+To+Speech), [`Search`](https://infron.ai/models?category=Search),  in [AI Model Marketplace](https://infron.ai/models).

For example about [z-ai/glm-5.2](https://infron.ai/models/z-ai/glm-5.2/api-reference)

```bash
curl https://llm.onerouter.pro/v1/chat/completions \
  -H "Authorization: Bearer $INFRON_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -d '{
    "model": "z-ai/glm-5.2",
    "messages": [
      {
        "role": "user",
        "content": "What is the meaning of life?"
      }
    ]
  }'
```

* **For** [**Anthropic SDK**](/docs/frameworks-and-integrations/anthropic-sdk-compatibility.md)

```python
import anthropic

client = anthropic.Anthropic(
    base_url="https://llm.onerouter.pro",
    api_key="<<Your API Key>>"
)

message = client.messages.create(
    model="anthropic/claude-sonnet-4.5",
    max_tokens=1000,
    temperature=1,
    system=[
        {
            "type": "text",
            "text": "You are a world-class poet. Respond only with short poems."
        }
    ],
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Why is the ocean salty?"
                }
            ]
        }
    ]
)

print(message.content)
```

</details>

<details>

<summary><strong>Step5: Explore your</strong> <a href="https://infron.ai/dashboard/discount"><strong>enterprise discount</strong></a> <strong>💰</strong></summary>

<figure><img src="/files/uYOjAjopTRsDuVMLUQag" alt=""><figcaption></figcaption></figure>

</details>

<details>

<summary><strong>Step6: Receipt Reimbursement 📃</strong></summary>

You can navigate to [Billing Page](https://infron.ai/dashboard/credits) to download receipts for your historical orders.

<figure><img src="/files/E5BEuTV9srDHsSq6J3MZ" alt=""><figcaption></figcaption></figure>

</details>

<details>

<summary><strong>Step7: Need enterprise support? 🏃🏻‍♀️🏃🏻</strong></summary>

* **📧 Technical support email**: <support@infron.ai>
* **Slack Group:** We set up a dedicated Slack channel for each enterprise client to provide one-on-one support; please contact <andrew.zheng@infron.ai>.
* **Whatsapp Group**: We set up a dedicated WA channel for each enterprise client to provide one-on-one support; please contact andrew.

<figure><img src="/files/nHJRBFbMJd9VitrE9oSB" alt="" width="103"><figcaption></figcaption></figure>

* **Telegram Group**: We set up a dedicated TG channel for each enterprise client to provide one-on-one support; please contact andrew.

<figure><img src="/files/FQNWq4GEc9iRHfcXLQ25" alt="" width="129"><figcaption></figcaption></figure>

* 💰 **Enterprise discount**: <https://infron.ai/contact>
* **🐦 X (Twitter)**: [@Infron](https://x.com/InfronAI) Get product updates, technical news, and industry insights.
* **💬 Discord**: <https://discord.com/invite/cbFS7RDeHq> Connect with other developers, get technical help, and stay up to date with the latest features.

</details>

### For agent builders

#### For Codex

*<mark style="color:$info;">**Paste into your Codex agent and follow the steps**</mark>*

```bash
codex plugin marketplace add InfronAI/infron-codex-plugin
  After installation, enable the infron plugin
  Set INFRON_API_KEY in your shell
  Tell me how to use Infron
```


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://infronai.gitbook.io/docs/overview/quickstart.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.