Make Your First API Call in 5 Minutes

This guide walks you through obtaining an API key and making your first request in 5 minutes. For registration and login steps, see Console Overview → Register an Account.

The examples in this guide are based on AI Model APIs (Chat, Embeddings, Audio, etc.). For complete API definitions, request parameters, and response formats, see API Reference → AI Model APIs.

Quick Start

Get an API Key

After logging into the console, click "API Keys" in the left sidebar, then click "Create Key" in the top right.

Enter a key name (e.g., my-first-key), leave the other options at their defaults, and click "Submit". The system will generate an API key starting with sk- for calling AI model APIs. For detailed steps, see Create an API Key.

The system will only display the full key once at creation time. Copy and save it somewhere secure immediately.

Get the API Endpoint

The platform's API is fully compatible with the OpenAI API format. Simply replace the Base URL with the platform address:

https://api.tokenopen.ai/v1

Make Your First Request

Replace YOUR_API_KEY in the code below with the API key you just created, then run it.

curl https://api.tokenopen.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-5.4-mini",
    "messages": [
      {
        "role": "user",
        "content": "Hello, please introduce yourself."
      }
    ]
  }'

from openai import OpenAI

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

response = client.chat.completions.create(
    model="gpt-5.4-mini",
    messages=[
        {"role": "user", "content": "Hello, please introduce yourself."}
    ],
)

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

import OpenAI from "openai";

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

const response = await client.chat.completions.create({
  model: "gpt-5.4-mini",
  messages: [
    { role: "user", content: "Hello, please introduce yourself." }
  ],
});

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

package main

import (
    "context"
    "fmt"

    "github.com/openai/openai-go"
    "github.com/openai/openai-go/option"
)

func main() {
    client := openai.NewClient(
        option.WithAPIKey("YOUR_API_KEY"),
        option.WithBaseURL("https://api.tokenopen.ai/v1"),
    )

    resp, err := client.Chat.Completions.New(context.Background(), openai.ChatCompletionNewParams{
        Model: openai.F("gpt-5.4-mini"),
        Messages: openai.F([]openai.ChatCompletionMessageParamUnion{
            openai.UserMessage("Hello, please introduce yourself."),
        }),
    })
    if err != nil {
        panic(err)
    }
    fmt.Println(resp.Choices[0].Message.Content)
}

API Parameters

Parameter	Type	Description
`model`	string	The model to call, e.g., `gpt-5.4-mini`, `claude-sonnet-4-6`
`messages`	array	Array of conversation messages; each message has a `role` and `content`
`temperature`	number	Optional. Controls output randomness; range 0–2, default 1
`max_tokens`	integer	Optional. Caps the maximum number of output tokens
`stream`	boolean	Optional. Set to `true` to enable streaming output

Streaming Output Example

from openai import OpenAI

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

stream = client.chat.completions.create(
    model="gpt-5.4-mini",
    messages=[{"role": "user", "content": "Write a short poem about spring."}],
    stream=True,
)

for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="", flush=True)

import OpenAI from "openai";

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

const stream = await client.chat.completions.create({
  model: "gpt-5.4-mini",
  messages: [{ role: "user", content: "Write a short poem about spring." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

Common Model Names

Model	Name
GPT-5.5	`gpt-5.5`
GPT-5.4	`gpt-5.4`
GPT-5.4-mini	`gpt-5.4-mini`
GPT-5.4-nano	`gpt-5.4-nano`
Claude Opus 4.7	`claude-opus-4-7`
Claude Sonnet 4.6	`claude-sonnet-4-6`
Gemini 3.5 Flash	`gemini-3.5-flash`
Gemini 3.1 Pro	`gemini-3.1-pro-preview`
DeepSeek-V4 Pro	`deepseek-v4-pro`
Qwen3-235B	`qwen3-235b-a22b`

For the full model list and real-time pricing, visit the "Pricing" page in the console.

Troubleshooting

Error Code	Cause	Solution
`401 Unauthorized`	API key is invalid or malformed	Check that the key is complete and starts with `sk-`
`403 Forbidden`	Current group has no access to this model	Switch to another model or contact support to upgrade your group
`429 Too Many Requests`	Rate limit exceeded	Reduce request frequency or apply for a higher-tier group
`402 Payment Required`	Insufficient account credits	Go to the Wallet page to top up
`500 Internal Server Error`	Upstream service temporarily unavailable	Retry later or switch to another model

Migrating from OpenAI

The platform is fully compatible with the OpenAI API protocol. Migration requires only two steps — no business logic changes needed.

Step 1: Replace the Base URL

Replace https://api.openai.com in your code or config with https://api.tokenopen.ai.

Step 2: Replace the API Key

Replace your OpenAI sk- key with an API key created in the platform console.

Original Variable	New Value
`OPENAI_API_KEY`	Platform API key (starts with `sk-`)
`OPENAI_BASE_URL`	`https://api.tokenopen.ai/v1`
`ANTHROPIC_BASE_URL`	`https://api.tokenopen.ai`

Once these two steps are complete, your application will route through this platform — no further changes required.

View Call Results

After making a call, go to "Logs" in the console to view real-time details for each request.

Field	Description
Time	Timestamp when the request was made
Model	The model used in this call
Key Name	The API key name used
Input Tokens	Number of input tokens consumed
Output Tokens	Number of output tokens generated
Credits Used	Credits deducted for this call
Status	Success / Failed / Timeout

For daily or per-model usage trends, visit the "Dashboard" page in the console.

Make Your First API Call in 5 Minutes

On this page