---
title: Quickstart
description: Get started with Agnic AI Gateway
---
# Quickstart
Agnic provides a unified API that gives you access to **340+ AI models** through a single endpoint. Get started with just a few lines of code using your preferred SDK or framework.
Looking for the full model list and pricing? Visit [AI Gateway Pricing](https://app.agnic.ai/ai-gateway/pricing).
---
## Using the OpenAI SDK
The fastest way to get started. Agnic is fully compatible with the OpenAI SDK - just change the base URL.
### Installation
```bash
# Python
pip install openai
# Node.js
npm install openai
```
### Python
```python
from openai import OpenAI
client = OpenAI(
base_url="https://api.agnic.ai/v1",
api_key="agnic_tok_YOUR_TOKEN",
)
completion = client.chat.completions.create(
model="openai/gpt-4o",
messages=[
{
"role": "user",
"content": "What is the meaning of life?"
}
]
)
print(completion.choices[0].message.content)
```
### TypeScript / JavaScript
```typescript
import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://api.agnic.ai/v1',
apiKey: 'agnic_tok_YOUR_TOKEN',
});
async function main() {
const completion = await client.chat.completions.create({
model: 'openai/gpt-4o',
messages: [
{
role: 'user',
content: 'What is the meaning of life?',
},
],
});
console.log(completion.choices[0].message.content);
}
main();
```
---
## Using the API Directly
Make requests directly to the Agnic API without any SDK.
### Python (requests)
```python
import requests
import json
response = requests.post(
url="https://api.agnic.ai/v1/chat/completions",
headers={
"Authorization": "Bearer agnic_tok_YOUR_TOKEN",
"Content-Type": "application/json",
},
json={
"model": "openai/gpt-4o",
"messages": [
{
"role": "user",
"content": "What is the meaning of life?"
}
]
}
)
print(response.json()["choices"][0]["message"]["content"])
```
### TypeScript (fetch)
```typescript
const response = await fetch('https://api.agnic.ai/v1/chat/completions', {
method: 'POST',
headers: {
'Authorization': 'Bearer agnic_tok_YOUR_TOKEN',
'Content-Type': 'application/json',
},
body: JSON.stringify({
model: 'openai/gpt-4o',
messages: [
{
role: 'user',
content: 'What is the meaning of life?',
},
],
}),
});
const data = await response.json();
console.log(data.choices[0].message.content);
```
### cURL
```bash
curl https://api.agnic.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer agnic_tok_YOUR_TOKEN" \
-d '{
"model": "openai/gpt-4o",
"messages": [
{
"role": "user",
"content": "What is the meaning of life?"
}
]
}'
```
---
## Try Different Models
Access models from all major providers with the same API:
```python
# OpenAI
completion = client.chat.completions.create(
model="openai/gpt-4o",
messages=[{"role": "user", "content": "Hello!"}]
)
# Anthropic Claude
completion = client.chat.completions.create(
model="anthropic/claude-3.5-sonnet",
messages=[{"role": "user", "content": "Hello!"}]
)
# Google Gemini
completion = client.chat.completions.create(
model="google/gemini-2.0-flash",
messages=[{"role": "user", "content": "Hello!"}]
)
# Meta Llama (Free!)
completion = client.chat.completions.create(
model="meta-llama/llama-3.3-70b",
messages=[{"role": "user", "content": "Hello!"}]
)
```
---
## Free Models
Start building without spending. These models are completely free:
| Model | Provider | Context |
|-------|----------|---------|
| `meta-llama/llama-3.3-70b` | Meta | 128K |
| `meta-llama/llama-3.1-8b` | Meta | 128K |
| `mistralai/mixtral-8x7b` | Mistral | 32K |
| `mistralai/mistral-7b` | Mistral | 32K |
```python
# Use free models for development
completion = client.chat.completions.create(
model="meta-llama/llama-3.3-70b", # Free!
messages=[{"role": "user", "content": "Write a poem about coding"}]
)
```
---
## Streaming Responses
Get responses in real-time:
```python
stream = client.chat.completions.create(
model="openai/gpt-4o",
messages=[{"role": "user", "content": "Write a short story"}],
stream=True
)
for chunk in stream:
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="")
```
For more details, see [Streaming](/docs/ai-gateway/streaming).
---
## Response Format
A successful response looks like:
```json
{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"model": "openai/gpt-4o",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "The meaning of life is a philosophical question..."
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 15,
"completion_tokens": 150,
"total_tokens": 165
}
}
```
---
## Authentication
Agnic supports two authentication methods:
| Method | Format | Use Case |
|--------|--------|----------|
| API Token | `agnic_tok_...` | Server-side, CI/CD |
| OAuth2 Token | `agnic_at_...` | User-authorized apps |
```python
# Using API Token
client = OpenAI(
base_url="https://api.agnic.ai/v1",
api_key="agnic_tok_YOUR_TOKEN",
)
# Using OAuth2 Token
client = OpenAI(
base_url="https://api.agnic.ai/v1",
api_key="agnic_at_YOUR_OAUTH_TOKEN",
)
```
---
## Error Handling
```python
from openai import OpenAI, APIError
client = OpenAI(
base_url="https://api.agnic.ai/v1",
api_key="agnic_tok_YOUR_TOKEN",
)
try:
completion = client.chat.completions.create(
model="openai/gpt-4o",
messages=[{"role": "user", "content": "Hello!"}]
)
print(completion.choices[0].message.content)
except APIError as e:
if e.status_code == 401:
print("Invalid API token")
elif e.status_code == 402:
print("Insufficient balance or spending limit exceeded")
elif e.status_code == 429:
print("Rate limit exceeded - try again later")
else:
print(f"API error: {e}")
```
---
## Next Steps
Browse 340+ models with pricing
Code examples in multiple languages
Real-time response streaming
Images, PDFs, audio, and video