Build AI agents with hundreds of models

vercel ai-gateway coding-agents setup

import { ToolLoopAgent, tool } from 'ai';
import { z } from 'zod';
 
const agent = new ToolLoopAgent({
  model: 'anthropic/claude-sonnet-5',
  tools: {
    getWeather: tool({
      description: 'Get the current weather for a location',
      inputSchema: z.object({ location: z.string() }),
      execute: async ({ location }) => ({
        location,
        temperature: 72,
        condition: 'sunny',
      }),
    }),
  },
});
 
const { text } = await agent.generate({
  prompt: "What's the weather in Tokyo?",
});
 
console.log(text);

curl https://ai-gateway.vercel.sh/v1/chat/completions \
  -H "Authorization: Bearer $AI_GATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-6-astra",
    "messages": [
      {
        "role": "user",
        "content": "Invent a new holiday and describe its traditions."
      }
    ]
  }'

AI Gateway works with the AI SDK, OpenAI Chat Completions, OpenAI Responses, Anthropic Messages, or your preferred framework.

Send images, files, audio, and video to compatible models, or connect them to application functions with tool use.

• One key, hundreds of models. Access models from multiple providers with a single API key
• Unified API. Switch between providers and models with minimal code changes
• High reliability. Automatically retries requests to other providers if one fails
• Embeddings support. Generate vector embeddings for search, retrieval, and other tasks
• Spend monitoring. Monitor your spending across different providers
• No markup on tokens. Tokens cost the same as they would from the provider directly, with zero markup, including with Bring Your Own Key (BYOK)

• AI Gateway pricing: Understand token costs, credits, add-on charges, and payment fees.
• Budgets and spend limits: Set spending limits and alerts for teams, projects, API keys, and users.
• Rate limits: Understand request limits and handle 429 responses.
• Security and compliance: Configure data retention, prompt training policies, and model and provider access.

Use the resources below to configure AI Gateway, or browse the AI Gateway guides for implementation patterns, templates, and troubleshooting.