Quick Start

Welcome to BigBangToken! This guide walks you through registration, obtaining an API key, and making your first model call.

1. Sign in to the platform

Visit the BigBangToken website, click Sign in in the top-right corner, and complete registration at the sign-in page.

2. Browse the model list

After signing in, open the pricing page to view supported models, pricing, and rate limits.

3. Try models in the playground

Open the Playground, choose a language or image model from the sidebar, enter a prompt, adjust parameters, and click Run to see results in real time.

4. Call the API

4.1 Create an API key

Go to API Keys and click Create API Key. Store the key securely and never share it publicly.

4.2 Call with the OpenAI SDK

Our API is fully compatible with the OpenAI protocol.

Choose your OS: Use the tab that matches your system — Linux / macOS for bash/zsh; Windows for PowerShell (recommended) or Windows Terminal. Do not paste Linux line continuations (\) into PowerShell.

Install dependencies: Copy the command from the matching tab (the Python example below works on all platforms).

Linux / macOS

pip install --upgrade openai

Windows

py -m pip install --upgrade openai

If py is not found on Windows, use python -m pip install --upgrade openai instead.

Examples: Pick Non-streaming or Streaming (controlled by the stream parameter).

Non-streaming

from openai import OpenAI

# Replace YOUR_API_KEY with your BigBangToken API key
client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://bigbangtoken.com/v1"
)

# Non-streaming: wait for the full completion in one JSON response
response = client.chat.completions.create(
    model="Pro/deepseek-ai/DeepSeek-R1",
    messages=[
        {"role": "user", "content": "Introduce yourself in one sentence."}
    ],
    stream=False  # default; may be omitted
)

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

Streaming

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://bigbangtoken.com/v1"
)

# Streaming: tokens arrive incrementally (good for live chat UIs)
stream = client.chat.completions.create(
    model="Pro/deepseek-ai/DeepSeek-R1",
    messages=[
        {"role": "user", "content": "Introduce yourself in one sentence."}
    ],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

4.3 Make a request (command line)

Replace YOUR_API_KEY with your API key, then copy the command from the tab that matches your system.

Linux / macOS: Open Terminal, paste the Linux / macOS curl command, and press Enter.

Windows · PowerShell: Use PowerShell or Windows Terminal (PowerShell profile). Copy the full script from the PowerShell tab.

Windows · CMD: If your prompt looks like C:\...> (Command Prompt), use the CMD tab. Line continuation is ^, not PowerShell's `.

Common mistakes

• Authorization must be Bearer YOUR_API_KEY (word Bearer, then a space, then your key). Sending only sk-... causes auth or parse errors.
• Do not paste PowerShell commands into CMD (you will see errors like '-N' is not recognized).
• Avoid -d '{...}' with curl.exe in PowerShell; use the PowerShell · Streaming tab (JSON file + --data-binary).

Choose your OS / shell and Non-streaming / Streaming. Use -N when "stream": true.

Linux / macOS · Non-streaming

# Non-streaming: one JSON response when complete
curl https://bigbangtoken.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "gpt-3.5-turbo",
  "messages": [{"role": "user", "content": "Say this is a test!"}],
  "temperature": 0.7,
  "stream": false
}'

Linux / macOS · Streaming

# Streaming: SSE chunks; -N disables curl buffering
curl https://bigbangtoken.com/v1/chat/completions \
  -N \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "gpt-3.5-turbo",
  "messages": [{"role": "user", "content": "Say this is a test!"}],
  "temperature": 0.7,
  "stream": true
}'

PowerShell · Non-streaming

$headers = @{
  "Content-Type" = "application/json"
  "Authorization" = "Bearer YOUR_API_KEY"
}

$body = @{
  model = "gpt-3.5-turbo"
  messages = @(
    @{ role = "user"; content = "Say this is a test!" }
  )
  temperature = 0.7
  stream = $false
} | ConvertTo-Json -Depth 5 -Compress

Invoke-RestMethod `
  -Uri "https://bigbangtoken.com/v1/chat/completions" `
  -Method Post `
  -Headers $headers `
  -Body $body

PowerShell · Streaming

$apiKey = "YOUR_API_KEY"

$payload = @{
  model = "gpt-3.5-turbo"
  messages = @(@{ role = "user"; content = "Say this is a test!" })
  temperature = 0.7
  stream = $true
} | ConvertTo-Json -Depth 5 -Compress

$jsonPath = "$env:TEMP\bb-chat-request.json"
[System.IO.File]::WriteAllText($jsonPath, $payload, (New-Object System.Text.UTF8Encoding $false))

curl.exe -N "https://bigbangtoken.com/v1/chat/completions" `
  -H "Content-Type: application/json" `
  -H "Authorization: Bearer $apiKey" `
  --data-binary "@$jsonPath"

CMD · Non-streaming

curl.exe -H "Content-Type: application/json" -H "Authorization: Bearer YOUR_API_KEY" -d "{\"model\":\"gpt-3.5-turbo\",\"messages\":[{\"role\":\"user\",\"content\":\"Say this is a test!\"}],\"temperature\":0.7,\"stream\":false}" https://bigbangtoken.com/v1/chat/completions

CMD · Streaming

curl.exe -N -H "Content-Type: application/json" -H "Authorization: Bearer YOUR_API_KEY" -d "{\"model\":\"gpt-3.5-turbo\",\"messages\":[{\"role\":\"user\",\"content\":\"Say this is a test!\"}],\"temperature\":0.7,\"stream\":true}" https://bigbangtoken.com/v1/chat/completions

Non-streaming response example (stream: false):

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1677858242,
  "model": "gpt-3.5-turbo-0301",
  "usage": {
    "prompt_tokens": 13,
    "completion_tokens": 7,
    "total_tokens": 20
  },
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "\n\nThis is a test!"
      },
      "finish_reason": "stop",
      "index": 0
    }
  ]
}

When finish_reason is stop, the API returned the full model completion. Set n to generate multiple choices in one request.

With streaming, the body is multiple data: {...} SSE lines; read incremental text from choices[0].delta.content until data: [DONE].

See the pricing page for available model IDs.