API Documentation

z0.chat provides an OpenAI-compatible API via the Vercel AI Gateway. Send one prompt to multiple models simultaneously, compare responses, and build with parallel inference. This API is 100% compatible with existing OpenAI SDKs — just change the base URL and API key.

Authentication

All requests require an API key passed in the Authorization header as a Bearer token. Get your API key from the z0.chat dashboard after signing in.

Authorization: Bearer z0-xxxxxxxxxxxxxxxxxxxx

Base URL

All API endpoints are relative to the base URL:

https://ai-gateway.vercel.sh/v1

Append the endpoint path to this base URL. For example, to call chat completions: https://ai-gateway.vercel.sh/v1/chat/completions

POST /chat/completions

curl -X POST https://ai-gateway.vercel.sh/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer z0-xxxxxxxxxxxx" \
  -d '{
    "model": "gpt-4o,claude-3.5-sonnet",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in 2 sentences."}
    ],
    "stream": false,
    "consensus": true
  }'

const res = await fetch("https://ai-gateway.vercel.sh/v1/chat/completions", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "Bearer z0-xxxxxxxxxxxx",
  },
  body: JSON.stringify({
    model: "gpt-4o,claude-3.5-sonnet",
    messages: [{ role: "user", content: "Explain quantum computing in 2 sentences." }],
    stream: false,
    consensus: true,
  }),
});
const data = await res.json();
console.log(data);

import requests

res = requests.post(
    "https://ai-gateway.vercel.sh/v1/chat/completions",
    headers={
        "Content-Type": "application/json",
        "Authorization": "Bearer z0-xxxxxxxxxxxx",
    },
    json={
        "model": "gpt-4o,claude-3.5-sonnet",
        "messages": [{"role": "user", "content": "Explain quantum computing in 2 sentences."}],
        "stream": False,
        "consensus": True,
    },
)
print(res.json())

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1700000000,
  "models": ["gpt-4o", "claude-3.5-sonnet"],
  "choices": [
    {
      "index": 0,
      "model": "gpt-4o",
      "message": {"role": "assistant", "content": "Quantum computing uses..."},
      "finish_reason": "stop"
    },
    {
      "index": 1,
      "model": "claude-3.5-sonnet",
      "message": {"role": "assistant", "content": "Quantum computing leverages..."},
      "finish_reason": "stop"
    }
  ],
  "consensus": {"score": 0.82, "agreement": "high"},
  "usage": {"prompt_tokens": 12, "completion_tokens": 48, "total_tokens": 60}
}

GET /models

curl https://ai-gateway.vercel.sh/v1/models \
  -H "Authorization: Bearer z0-xxxxxxxxxxxx"

{
  "object": "list",
  "data": [
    {"id": "gpt-4o", "provider": "openai", "context": 128000},
    {"id": "claude-3.5-sonnet", "provider": "anthropic", "context": 200000},
    {"id": "llama-3.1-70b", "provider": "meta", "context": 131072},
    {"id": "mistral-large", "provider": "mistral", "context": 128000}
  ]
}

Code Examples

Streaming with SSE

const res = await fetch("https://ai-gateway.vercel.sh/v1/chat/completions", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": `Bearer ${apiKey}`,
  },
  body: JSON.stringify({
    model: "gpt-4o,claude-3.5-sonnet",
    messages: [{ role: "user", content: "Write a haiku about the ocean." }],
    stream: true,
  }),
});
const reader = res.body.getReader();
const decoder = new TextDecoder();
while (true) {
  const { done, value } = await reader.read();
  if (done) break;
  const chunk = decoder.decode(value);
  chunk.split("\n").forEach((line) => {
    if (line.startsWith("data: ")) {
      const data = JSON.parse(line.slice(6));
      console.log(data.model, "→", data.choices[0]?.delta?.content || "");
    }
  });
}

Error Codes

Rate Limits

Rate limits are applied per API key and vary by tier. All responses include X-RateLimit-Limit, X-RateLimit-Remaining, and X-RateLimit-Reset headers.

SDK Examples

OpenAI SDK (JavaScript)

import OpenAI from "openai";
const client = new OpenAI({
  apiKey: process.env.Z0_API_KEY,
  baseURL: "https://ai-gateway.vercel.sh/v1",
});
const res = await client.chat.completions.create({
  model: "gpt-4o,claude-3.5-sonnet",
  messages: [{ role: "user", content: "Hello, z0!" }],
});
console.log(res.choices);

OpenAI SDK (Python)

from openai import OpenAI
client = OpenAI(
    api_key=os.environ["Z0_API_KEY"],
    base_url="https://ai-gateway.vercel.sh/v1",
)
res = client.chat.completions.create(
    model="gpt-4o,claude-3.5-sonnet",
    messages=[{"role": "user", "content": "Hello, z0!"}],
)
print(res.choices)

LangChain Integration

from langchain_openai import ChatOpenAI
llm = ChatOpenAI(
    model="gpt-4o",
    api_key=os.environ["Z0_API_KEY"],
    base_url="https://ai-gateway.vercel.sh/v1",
)
response = llm.invoke("What is multi-model inference?")