Vercel AI Gateway Integration
Route Vercel AI Gateway requests through Superagent for enhanced security
Superagent can be configured to work with Vercel AI Gateway by configuring the gateway provider with your Superagent proxy URL. This adds AI firewall protection to your multi-provider AI applications.
AI SDK with Gateway Provider
import { gateway } from '@ai-sdk/gateway';
import { generateText } from 'ai';
const gatewayProvider = gateway({
apiKey: 'your-vercel-ai-gateway-api-key',
baseURL: 'YOUR_SUPERAGENT_PROXY_URL', // Replace with your Superagent proxy
});
// Use with any Vercel AI Gateway model
const { text } = await generateText({
model: gatewayProvider('xai/grok-3'),
prompt: 'Explain quantum computing',
});
Direct Model Specification
import { generateText } from 'ai';
// Configure gateway globally with Superagent proxy
const { text } = await generateText({
model: 'xai/grok-3', // Direct model specification
prompt: 'Hello world',
});
Python (OpenAI SDK Compatible)
from openai import OpenAI
client = OpenAI(
api_key="your-vercel-ai-gateway-api-key",
base_url="YOUR_SUPERAGENT_PROXY_URL" # Replace with your Superagent proxy
)
# Use any model from Vercel AI Gateway
response = client.chat.completions.create(
model="xai/grok-3",
messages=[{"role": "user", "content": "Hello world"}]
)
TypeScript/JavaScript (OpenAI SDK)
import OpenAI from 'openai';
const client = new OpenAI({
apiKey: 'your-vercel-ai-gateway-api-key',
baseURL: 'YOUR_SUPERAGENT_PROXY_URL', // Replace with your Superagent proxy
});
// Use any model from Vercel AI Gateway
const response = await client.chat.completions.create({
model: 'openai/gpt-4o',
messages: [{ role: 'user', content: 'Hello world' }],
});
Embeddings
import { embed } from 'ai';
const { embedding } = await embed({
model: 'openai/text-embedding-3-small',
value: 'Your text to embed',
});
Available Models
Popular models accessible through Vercel AI Gateway:
- xAI:
xai/grok-3
,xai/grok-2
- OpenAI:
openai/gpt-4o
,openai/gpt-4o-mini
,openai/gpt-3.5-turbo
- Anthropic:
anthropic/claude-3-5-sonnet-20241022
- Google:
google/gemini-2.0-flash-exp
,google/gemini-1.5-pro
- Meta:
meta/llama-3.1-405b-instruct
,meta/llama-3.1-70b-instruct
- Mistral:
mistral/mistral-large-2411
,mistral/pixtral-12b-2409
Dynamic Model Discovery
import { gateway } from '@ai-sdk/gateway';
const gatewayProvider = gateway({
apiKey: 'your-vercel-ai-gateway-api-key',
baseURL: 'YOUR_SUPERAGENT_PROXY_URL',
});
// Get all available models
const models = await gatewayProvider.getAvailableModels();
// Filter by type
const languageModels = models.filter(model => model.type === 'language');
const embeddingModels = models.filter(model => model.type === 'embedding');
Configuration Benefits
- Multi-Provider Protection: Secure access to 100+ AI models through one proxy
- Unified Security: Consistent threat detection across all providers
- No Provider Management: Keep Vercel's unified API while adding security
- Model Discovery: Dynamic model listing with added protection
- Easy Switching: Switch between models while maintaining security
Migration Notes
- Gateway Provider: Use
@ai-sdk/gateway
with custom baseURL - Model Format: Use
provider/model-name
format (e.g.,xai/grok-3
) - All Features Supported: Streaming, embeddings, function calling work normally
- Added Security: All requests now protected by Superagent's AI firewall
Configure the gateway provider with your Superagent proxy URL to add comprehensive AI security to your multi-provider setup!