AI Pipe

AI Pipe lets you build web apps that can access LLM APIs (e.g. OpenRouter, OpenAI, Gemini etc.) without a back-end.

An instance is hosted at https://aipipe.org/. You can host your own on CloudFlare. Licensed under MIT.

User Guide

Visit these pages:

• aipipe.org to understand how it works.
• aipipe.org/login with a Google Account to get your AI Pipe Token and track your usage.
• aipipe.org/playground to explore models and chat with them.

AI Pipe Token

You can use the AI Pipe Token from aipipe.org/login in any OpenAI API compatible application by setting:

• OPENAI_API_KEY as your AI Pipe Token
• OPENAI_BASE_URL as https://aipipe.org/openai/v1

For example:

export OPENAI_API_KEY=$AIPIPE_TOKEN
export OPENAI_BASE_URL=https://aipipe.org/openai/v1

Now you can run:

uvx openai api chat.completions.create -m gpt-5-nano -g user "Hello"

... or:

uvx llm 'Hello' -m gpt-5-nano --key $AIPIPE_TOKEN

This will print something like Hello! How can I assist you today?

Native Provider API Keys

You can also use your own provider API keys directly (instead of an AI Pipe Token). This is useful if you want to:

• Bypass AI Pipe's cost tracking and budget limits
• Use models that aren't yet in AI Pipe's pricing database
• Handle billing directly with the provider

Simply use your native API key in the Authorization header:

# OpenAI with native key (starts with sk-)
curl https://aipipe.org/openai/v1/chat/completions \
  -H "Authorization: Bearer sk-your-openai-key" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-5-nano", "messages": [{"role": "user", "content": "Hello"}]}'

# OpenRouter with native key (starts with sk-or-)
curl https://aipipe.org/openrouter/v1/chat/completions \
  -H "Authorization: Bearer sk-or-your-openrouter-key" \
  -H "Content-Type: application/json" \
  -d '{"model": "openai/gpt-5-nano", "messages": [{"role": "user", "content": "Hello"}]}'

# Gemini with native key (starts with AIza)
curl https://aipipe.org/geminiv1beta/models/gemini-2.5-flash-lite:generateContent \
  -H "Authorization: Bearer AIzaSyYourGeminiKey" \
  -H "Content-Type: application/json" \
  -d '{"contents":[{"parts":[{"text":"Hello"}]}]}'

Native keys are detected by their prefix pattern:

• OpenAI / OpenRouter: Keys starting with sk-
• Google Gemini: Keys starting with AIza

Note: Native API keys cannot access /usage or /admin endpoints, which require an AI Pipe Token.

Developer Guide

Paste this code into index.html, open it in a browser, and check your DevTools Console

<script type="module">
  import { getProfile } from "https://aipipe.org/aipipe.js";

  const { token, email } = getProfile();
  if (!token) window.location = `https://aipipe.org/login?redirect=${window.location.href}`;

  const response = await fetch("https://aipipe.org/openrouter/v1/chat/completions", {
    method: "POST",
    headers: { Authorization: `Bearer ${token}`, "Content-Type": "application/json" },
    body: JSON.stringify({
      model: "openai/gpt-5-nano",
      messages: [{ role: "user", content: "What is 2 + 2?" }],
    }),
  }).then((r) => r.json());
  console.log(response);
</script>

This app will:

1. Redirect the user to AI Pipe.
   • getProfile() sets token to null since it doesn't know the user.
   • window.location redirects the user to https://aipipe.org/login with ?redirect= as your app URL
2. Redirect them back to your app once they log in.

• Your app URL will have a ?aipipe_token=...&aipipe_email=... with the user's token and email
• getProfile() fetches these, stores them for future reference, and returns token and email

3. Make an LLM API call to OpenRouter or OpenAI and log the response.

• You can replace any call to https://openrouter.ai/api/v1 with https://aipipe.org/openrouter/v1 and provide Authorization: Bearer $AIPIPE_TOKEN as a header.
• Similarly, you can replace https://api.openai.com/v1 with https://aipipe.org/openai/v1 and provide Authorization: Bearer $AIPIPE_TOKEN as a header.
• AI Pipe replaces the token and proxies the request via the provider.

API

GET /usage: Returns usage data for specified email and time period

Example: Get usage for a user

curl https://aipipe.org/usage -H "Authorization: Bearer $AIPIPE_TOKEN"

Response:

{
  "email": "user@example.com",
  "days": 7,
  "cost": 0.000137,
  "usage": [{ "date": "2025-04-16", "cost": 0.000137 }],
  "limit": 0.1
}

GET /proxy/[URL]: Proxies requests to the specified URL, bypassing CORS restrictions. No authentication required.

Example: Get contents of a URL

curl "https://aipipe.org/proxy/https://httpbin.org/get?x=1"

Response:

{
  "args": { "x": "1" },
  "headers": {
    "Accept": "*/*",
    "Host": "httpbin.org",
    "User-Agent": "curl/8.5.0"
  },
  "origin": "45.123.26.54",
  "url": "https://httpbin.org/get?x=1"
}

Notes:

• The response includes the original URL in the X-Proxy-URL header
• URLs must begin with http or https
• Requests timeout after 30 seconds
• All HTTP methods (GET, POST, etc.) and headers are preserved
• CORS headers are added for browser compatibility

GET token?credential=...: Converts a Google Sign-In credential into an AI Pipe token:

• When a user clicks "Sign in with Google" on the login page, Google's client library returns a JWT credential
• The login page sends this credential to /token?credential=...
• AI Pipe verifies the credential using Google's public keys
• If valid, AI Pipe signs a new token containing the user's email (and optional salt) using AIPIPE_SECRET
• Returns: { token, email ... } where additional fields come from Google's profile

OpenRouter API

GET /openrouter/*: Proxy requests to OpenRouter

Example: List Openrouter models

curl https://aipipe.org/openrouter/v1/models -H "Authorization: Bearer $AIPIPE_TOKEN"

Response:

{
  "data": [
    {
      "id": "google/gemini-2.5-pro-preview-03-25",
      "name": "Google: Gemini 2.5 Pro Preview"
      // ...
    }
  ]
}

Example: Make a chat completion request

curl https://aipipe.org/openrouter/v1/chat/completions \
  -H "Authorization: Bearer $AIPIPE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model": "google/gemini-2.0-flash-lite-001", "messages": [{ "role": "user", "content": "What is 2 + 2?" }] }'

Response contains:

{ "choices": [{ "message": { "role": "assistant", "content": "..." } }] }

OpenRouter Image Generation

curl https://aipipe.org/openrouter/v1/chat/completions \
  -H "Authorization: Bearer $AIPIPE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-2.5-flash-image-preview",
    "messages": [{"role": "user", "content": "Draw a cat"}],
    "modalities": ["image", "text"]
  }'

Response contains:

{
  "choices": [
    {
      "message": {
        "images": [
          {
            "type": "image_url",
            "image_url": { "url": "data:image/png;base64,iVBORw0K..." }
          }
        ]
      }
    }
  ]
}

OpenAI API

GET /openai/*: Proxy requests to OpenAI

AIPipe supports all OpenAI models that return usage data in their responses, enabling accurate cost tracking. This includes chat completion models, audio preview models (e.g. gpt-4o-audio-preview), and transcription models (e.g. gpt-4o-transcribe). Text-to-speech (TTS) models like tts-1 are not supported because they return raw audio without usage metadata.

Example: List OpenAI models

curl https://aipipe.org/openai/v1/models -H "Authorization: Bearer $AIPIPE_TOKEN"

Response contains:

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4o-audio-preview-2024-12-17",
      "object": "model",
      "created": 1734034239,
      "owned_by": "system"
    }
    // ...
  ]
}

Example: Make a responses request

curl https://aipipe.org/openai/v1/responses \
  -H "Authorization: Bearer $AIPIPE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-5-nano", "input": "What is 2 + 2?" }'

Response contains:

{
  "output": [{
    "role": "assistant",
    "content": [{ "text": "2 + 2 equals 4." }] // ...
  }]
}

Example: Create embeddings

curl https://aipipe.org/openai/v1/embeddings \
  -H "Authorization: Bearer $AIPIPE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model": "text-embedding-3-small", "input": "What is 2 + 2?" }'

Response contains:

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.010576399, -0.037246477 // ...
      ]
    }
  ],
  "model": "text-embedding-3-small",
  "usage": { "prompt_tokens": 8, "total_tokens": 8 }
}

Gemini API

GET /geminiv1beta/*: Proxy requests to Google's Gemini API

Example: Make a generateContent request

curl https://aipipe.org/geminiv1beta/models/gemini-2.5-flash-lite:generateContent \
  -H "x-goog-api-key: $AIPIPE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"contents":[{"parts":[{"text":"What is 2 + 2?"}]}]}'

Response contains:

{
  "candidates": [{ "content": { "parts": [{ "text": "2 + 2 is 4."