Quickstart

Anyone is compatible with the OpenAI API format, so any tool or SDK that supports OpenAI works out of the box — just change the base URL and API key.

Get started

Go to anyone.ai and create an account
Log in and open the Dashboard
Click API Keys → Create API Key
Give your API key a name, then click Submit
Copy the API key (it is only shown once)

A token is your credential for calling the API. We recommend using different tokens for different projects to track usage separately.

Send your first request

Call the API with your API key. Replace YOUR_TOKEN with the API key you just copied.

curl https://api.anyone.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -d '{
    "model": "gpt-5.4",
    "messages": [
      {"role": "user", "content": "Say hello in one sentence."}
    ]
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.anyone.ai/v1",
    api_key="YOUR_TOKEN",
)

response = client.chat.completions.create(
    model="gpt-5.4",
    messages=[
        {"role": "user", "content": "Say hello in one sentence."}
    ],
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.anyone.ai/v1",
  apiKey: "YOUR_TOKEN",
});

const response = await client.chat.completions.create({
  model: "gpt-5.4",
  messages: [{ role: "user", content: "Say hello in one sentence." }],
});

console.log(response.choices[0].message.content);

Example response:

{
  "id": "chatcmpl-...",
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "Hello! Great to meet you."
      }
    }
  ],
  "usage": {
    "prompt_tokens": 13,
    "completion_tokens": 10,
    "total_tokens": 23
  }
}

Any tool compatible with the OpenAI API works directly with Anyone, including LangChain, LlamaIndex, Vercel AI SDK, Cherry Studio, and more. Just set the base URL and API key.

Try other models

Change the model name to use a different model — no other code changes needed:

# Claude
response = client.chat.completions.create(
    model="claude-sonnet-4-6",
    messages=[{"role": "user", "content": "Hello"}],
)

# Gemini
response = client.chat.completions.create(
    model="gemini-3.1-pro-preview",
    messages=[{"role": "user", "content": "Hello"}],
)

# DeepSeek
response = client.chat.completions.create(
    model="DeepSeek-V3.2",
    messages=[{"role": "user", "content": "Hello"}],
)

Check your usage

Go to the Logs page in the dashboard to see details for each request: model, token usage, and cost. The Analytics page has summary charts.

Common use cases

Use Claude models

Call Claude via OpenAI format, or use the native Claude Messages format.

View all models

Call /v1/models to get the full list of available models.

Top up

Learn about top-up methods and pricing.

Format conversion

Using the OpenAI SDK to call Claude/Gemini? Anyone converts formats automatically.

⌘I

Get Started

Basics

Guides

Help

Get started

Common use cases

Use Claude models

View all models

Top up

Format conversion

​Get started

​Common use cases

Use Claude models

View all models

Top up

Format conversion

Get started

Common use cases