Quickstart

Get started with AIRouter in minutes. Choose your preferred API style:

💡

Base URL: https://airouter.zbstream.com/v1

Install SDK

pip install openai

npm install openai

Make Your First Request

from openai import OpenAI

client = OpenAI(
    base_url="https://airouter.zbstream.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="llama3.2:latest",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://airouter.zbstream.com/v1",
  apiKey: "YOUR_API_KEY"
});

const response = await client.chat.completions.create({
  model: "llama3.2:latest",
  messages: [{ role: "user", content: "Hello!" }]
});

console.log(response.choices[0].message.content);

curl https://airouter.zbstream.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama3.2:latest",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

🦙

Base URL: https://airouter.zbstream.com (no /v1)

No SDK Required

Ollama native API uses simple HTTP requests. Just use requests (Python) or fetch (JavaScript).

pip install requests

Make Your First Request

import requests

response = requests.post(
    "https://airouter.zbstream.com/api/chat",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    },
    json={
        "model": "llama3.2:latest",
        "messages": [
            {"role": "user", "content": "Hello!"}
        ]
    }
)

print(response.json()["message"]["content"])

const response = await fetch("https://airouter.zbstream.com/api/chat", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "llama3.2:latest",
    messages: [{ role: "user", content: "Hello!" }]
  })
});

const data = await response.json();
console.log(data.message.content);

curl https://airouter.zbstream.com/api/chat \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama3.2:latest",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Authentication

All API requests require an API key for authentication.

Getting Your API Key

Create an account at Sign Up
Go to your Dashboard
Navigate to "API Keys" section
Click "Create New API Key"

Using Your API Key

Include your API key in the Authorization header:

Authorization: Bearer YOUR_API_KEY

Models

AIRouter provides access to 550+ models across 500+ global endpoints.

Popular Models

Model	Description	Use Case
`llama3.2:latest`	Meta's latest Llama model	General purpose
`qwen2.5:7b`	Alibaba's multilingual model	Multilingual tasks
`deepseek-r1:7b`	Advanced reasoning model	Complex reasoning
`codellama:7b`	Code-specialized Llama	Code generation
`llava:7b`	Vision-language model	Image understanding

Browse all models →

Chat Completions

Generate conversational responses using chat models.

🟢 OpenAI Compatible

POST /v1/chat/completions

🦙 Ollama Native

POST /api/chat

Request Parameters

Parameter	Type	Required	Description
`model`	string	Yes	Model ID (e.g., "llama3.2:latest")
`messages`	array	Yes	Array of message objects
`stream`	boolean	No	Enable streaming (default: false)
`temperature`	number	No	Sampling temperature (0-2)
`max_tokens`	integer	No	Maximum tokens to generate

OpenAI Compatible Example

from openai import OpenAI

client = OpenAI(
    base_url="https://airouter.zbstream.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="llama3.2:latest",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of France?"}
    ],
    temperature=0.7
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://airouter.zbstream.com/v1",
  apiKey: "YOUR_API_KEY"
});

const response = await client.chat.completions.create({
  model: "llama3.2:latest",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "What is the capital of France?" }
  ],
  temperature: 0.7
});

console.log(response.choices[0].message.content);

curl https://airouter.zbstream.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama3.2:latest",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is the capital of France?"}
    ],
    "temperature": 0.7
  }'

Ollama Native Example

import requests

response = requests.post(
    "https://airouter.zbstream.com/api/chat",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    },
    json={
        "model": "llama3.2:latest",
        "messages": [
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "What is the capital of France?"}
        ]
    }
)

print(response.json()["message"]["content"])

const response = await fetch("https://airouter.zbstream.com/api/chat", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "llama3.2:latest",
    messages: [
      { role: "system", content: "You are a helpful assistant." },
      { role: "user", content: "What is the capital of France?" }
    ]
  })
});

const data = await response.json();
console.log(data.message.content);

curl https://airouter.zbstream.com/api/chat \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama3.2:latest",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is the capital of France?"}
    ]
  }'

Streaming

Stream responses in real-time for better user experience.

🟢 OpenAI Compatible

Returns SSE format (Server-Sent Events)

🦙 Ollama Native

Returns NDJSON format (newline-delimited JSON)

OpenAI Compatible Streaming

from openai import OpenAI

client = OpenAI(
    base_url="https://airouter.zbstream.com/v1",
    api_key="YOUR_API_KEY"
)

stream = client.chat.completions.create(
    model="llama3.2:latest",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://airouter.zbstream.com/v1",
  apiKey: "YOUR_API_KEY"
});

const stream = await client.chat.completions.create({
  model: "llama3.2:latest",
  messages: [{ role: "user", content: "Tell me a story" }],
  stream: true
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}

Ollama Native Streaming

import requests

response = requests.post(
    "https://airouter.zbstream.com/api/chat",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "llama3.2:latest",
        "messages": [{"role": "user", "content": "Tell me a story"}],
        "stream": True
    },
    stream=True
)

for line in response.iter_lines():
    if line:
        data = json.loads(line)
        print(data.get("message", {}).get("content", ""), end="")

const response = await fetch("https://airouter.zbstream.com/api/chat", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "llama3.2:latest",
    messages: [{ role: "user", content: "Tell me a story" }],
    stream: true
  })
});

const reader = response.body.getReader();
const decoder = new TextDecoder();

while (true) {
  const { done, value } = await reader.read();
  if (done) break;
  const lines = decoder.decode(value).split("\\n");
  for (const line of lines) {
    if (line) {
      const data = JSON.parse(line);
      process.stdout.write(data.message?.content || "");
    }
  }
}

List Models

Retrieve the list of available models.

GET /v1/models

🔓

Note: This endpoint is public and does not require authentication.

Example

from openai import OpenAI

client = OpenAI(
    base_url="https://airouter.zbstream.com/v1",
    api_key="YOUR_API_KEY"
)

models = client.models.list()
for model in models.data:
    print(model.id)

curl https://airouter.zbstream.com/v1/models

OpenAI SDK

AIRouter is fully compatible with the official OpenAI SDK.

Configuration

Simply change the base_url to use AIRouter:

from openai import OpenAI

# Just change base_url to use AIRouter
client = OpenAI(
    base_url="https://airouter.zbstream.com/v1",
    api_key="YOUR_AIROUTER_API_KEY"
)

# Use any Ollama model
response = client.chat.completions.create(
    model="llama3.2:latest",
    messages=[{"role": "user", "content": "Hello!"}]
)

import OpenAI from "openai";

// Just change baseURL to use AIRouter
const client = new OpenAI({
  baseURL: "https://airouter.zbstream.com/v1",
  apiKey: "YOUR_AIROUTER_API_KEY"
});

// Use any Ollama model
const response = await client.chat.completions.create({
  model: "llama3.2:latest",
  messages: [{ role: "user", content: "Hello!" }]
});

Ollama Native API

Use Ollama's native API format for direct integration.

POST /api/chat

POST /api/generate

Example

import requests

response = requests.post(
    "https://airouter.zbstream.com/api/chat",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "llama3.2:latest",
        "messages": [{"role": "user", "content": "Hello!"}]
    }
)

print(response.json())

curl https://airouter.zbstream.com/api/chat \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama3.2:latest",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Text Completions

Generate text completions from a prompt.

🟢 OpenAI Compatible

POST /v1/completions

🦙 Ollama Native

POST /api/generate

Request Parameters

Parameter	Type	Required	Description
`model`	string	Yes	Model ID
`prompt`	string	Yes	Text prompt to complete
`max_tokens`	integer	No	Maximum tokens to generate
`stream`	boolean	No	Enable streaming

OpenAI Compatible Example

curl https://airouter.zbstream.com/v1/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama3.2:latest",
    "prompt": "Write a poem about AI:"
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://airouter.zbstream.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.completions.create(
    model="llama3.2:latest",
    prompt="Write a poem about AI:"
)

print(response.choices[0].text)

Ollama Native Example

curl https://airouter.zbstream.com/api/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama3.2:latest",
    "prompt": "Write a poem about AI:"
  }'

import requests

response = requests.post(
    "https://airouter.zbstream.com/api/generate",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "llama3.2:latest",
        "prompt": "Write a poem about AI:"
    }
)

print(response.json()["response"])