Get started

Merge Gateway puts every LLM behind a single API, with intelligent routing, cost management, and security built in. Route to OpenAI, Anthropic, Google, and AWS Bedrock through a single endpoint, with automatic failover and observability.

Signing up needs no card. The free plan comes with credit to spend on its model list, and paid traffic is the provider’s price for the tokens plus a 5% Merge fee. Plans and pricing covers the rest.

Merge Gateway SDK

pip install merge-gateway-python

from merge_gateway import MergeGateway
client = MergeGateway(api_key="YOUR_API_KEY")
response = client.responses.create(
    model="openai/gpt-5.2",
    input=[
        {"type": "message", "role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
        {"type": "message", "role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
    ],
)
print(response.output[0].content[0].text)

response = client.responses.create(
    model="anthropic/claude-sonnet-5",
    input=[
        {"type": "message", "role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
        {"type": "message", "role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
    ],
)

OpenAI SDK

Already using the OpenAI SDK? Point it at Merge Gateway to get multi-provider routing without changing your application code.

from openai import OpenAI
client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api-gateway.merge.dev/v1/openai",
)

response = client.chat.completions.create(
    model="gpt-5.2",
    messages=[
        {"role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
        {"role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
    ],
)
print(response.choices[0].message.content)

AI SDK (Vercel)

Using the Vercel AI SDK? Use the Merge Gateway provider for full access to routing, tags, and cost tracking, or use the quick-start URL shim for zero-install setup.

Recommended: Merge Gateway provider

npm install merge-gateway-ai-sdk-provider ai

import { createMergeGateway } from "merge-gateway-ai-sdk-provider";
const gateway = createMergeGateway({
  apiKey: "YOUR_API_KEY",
});

import { generateText } from "ai";
const { text } = await generateText({
  model: gateway("openai/gpt-5.5"),
  prompt: "Explain the concept of recursion in programming with a simple set of examples.",
});
console.log(text);

The native provider gives you typed access to Gateway features like tags, vendor routing, routing metadata, and structured-output strict control via providerOptions.mergeGateway. generateObject and streamObject map to Gateway’s native json_schema structured output — see Structured outputs.

import { createMergeGateway } from "merge-gateway-ai-sdk-provider/v5";

Alternative: URL shim (no extra install)

If you already have @ai-sdk/openai installed, point it at Gateway with a base URL change:

import { createOpenAI } from "@ai-sdk/openai";
const gateway = createOpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://api-gateway.merge.dev/v1/ai-sdk",
});
// All generateText/streamText calls work unchanged

Other SDKs

Gateway is compatible with any SDK that lets you set a custom base URL.

Where two base URLs are listed, both accept the same requests. The second is each SDK’s default base URL shape: the OpenAI SDK appends chat/completions to a /v1 base URL, and the Anthropic SDK appends /v1/messages to the host, so the only change from the vendor’s own base URL is the host. Two exceptions: the OpenAI SDK’s client.responses.* at the /v1 base URL reaches /v1/responses, which is Gateway’s native Responses API rather than OpenAI’s, so use the /v1/openai base URL when you call the Responses API; and the Anthropic SDK’s models.list() at the bare host returns Gateway’s native model listing, so use the /v1/anthropic base URL if you need Anthropic-shaped model listings.

from anthropic import Anthropic
client = Anthropic(
    api_key="YOUR_API_KEY",
    base_url="https://api-gateway.merge.dev/v1/anthropic",
)
message = client.messages.create(
    model="anthropic/claude-sonnet-5",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
    ],
)
print(message.content[0].text)

Next steps