NEWKimi-K3 just onboarded — $3.3/M in · $16.5/M out.Try it →

DEVELOPER DOCUMENTATION

Build With EasyToken API

One key, one API, access to top models. This page covers the core setup and integration flow for token platform users.

Start onboarding View pricing

Quick Start

Follow these five steps to go from account signup to your first successful API call.

Step

Create an account

Step

Generate an API key

Open Console -> API Keys -> Create key.

Step

Prepay your balance

Recharge extra credit in Billing.

Step

Make your first request

Call the OpenAI-compatible endpoint with your key and preferred model.

Step

Track usage and spend

Monitor token usage, request volume, and cost in the Billing dashboard.

Authentication

Use a secret API key in the Authorization header. Never expose this key in browser-side code.

Security best practice

Store keys in server environment variables, rotate on schedule, and revoke immediately if leaked.

Example request · OpenAI Python SDK

from openai import OpenAI

client = OpenAI(
    api_key="<Your_api_key>",
    base_url="https://api.easytoken.site/v1"
)

response = client.chat.completions.create(
    model="deepseek-v3.2",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Summarize this product update."}
    ],
    temperature=0.3
)

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

Basic Platform Capabilities

Unified model access

Call multiple providers through one API endpoint and one account balance.

OpenAI-style request format

Reuse your existing OpenAI-compatible payload structure with minimal changes.

Usage and billing visibility

Check token usage and spend in the console to manage your prepaid balance.

API Modes

EasyToken provides three basic modes. Start with one mode, then expand as your product needs grow.

Text

For chatbots, Q and A, summarization, extraction, and generation.

Basic endpoint

POST /chat/completions

Request and Response Examples

Review the text chat request and response format returned by the OpenAI-compatible endpoint.

Text Mode

Chatbots, Q&A, summarization, extraction, and generation.

Endpoint

POST /chat/completions

Request

POST /chat/completions
{
  "model": "deepseek-v3.2",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Summarize this product update."}
  ],
  "temperature": 0.3
}

Response

{
  "id": "chatcmpl_xxx",
  "object": "chat.completion",
  "model": "deepseek-v3.2",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The update adds prepaid billing, better usage visibility, and a simpler API onboarding flow."
      },
      "finish_reason": "stop"
    }
  ]
}

API Usage Notes

Base URL

Use https://api.easytoken.site/v1 for all requests.

Compatible format

Endpoints follow OpenAI-style schemas, so existing SDK integrations are easy to migrate.

Rate limits

Limits vary by plan and model. Handle HTTP 429 with exponential backoff and retries.

Error handling

Log request id and status code. Common responses: 400, 401, 403, 429, 500.

Billing and Usage

EasyToken uses prepaid billing based on input/output token usage. Add balance first, then monitor remaining credit and spend in your dashboard.

Item	What to monitor	Where
Token usage	Input and output tokens per model	Usage dashboard
Remaining balance	Available prepaid credit after requests	Billing overview
Invoice history	Top-ups and payment records	Billing history

Need More Details?

EasyToken docs are intentionally simple. For model choices and pricing rates, continue with the model list and pricing pages.

Browse models Billing details