API Documentation & Quickstart

Authentication & Base URL

Your API key authenticates every request to our base URL: https://api.chatgptapicost.com/v1. We support standard header-based auth. Send your key in the Authorization header as a Bearer token. This works with the official OpenAI SDKs and any compatible client.

• Base URL: https://api.chatgptapicost.com/v1
• Auth Header: Authorization: Bearer YOUR_API_KEY
• Model ID: uncensored

Copycurl https://api.chatgptapicost.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the standard per token pricing tiers."}]
  }'

The /v1/chat/completions Endpoint

Send your prompt to POST /v1/chat/completions and receive text output. The endpoint accepts a messages array containing your conversation history. Each message requires a role (user, assistant, system) and content string. We charge by real token usage, not per request.

• Input Price: $0.15 per 1M input tokens
• Output Price: $0.50 per 1M output tokens
• Error Handling: Refusals and errors incur zero charge

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.chatgptapicost.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Streaming & Token Usage

Enable streaming by setting stream: true. The API returns Server-Sent Events (SSE). Token usage metadata appears only in the final chunk. This allows you to track consumption in real-time without waiting for full generation. Streaming reduces perceived latency for high-volume applications.

• Format: Server-Sent Events (SSE)
• Usage Data: Available in the last chunk only
• Benefits: Lower latency perception, real-time progress

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Function Calling & JSON Mode

Use tools and tool_choice for function calling. Specify response_format: {"type": "json_object"} for strict JSON output. This ensures structured data for your pipelines. The model supports both structured and conversational outputs seamlessly.

• JSON Mode: response_format: {"type": "json_object"}
• Function Calling: Standard OpenAI tool format
• Compatibility: Works with existing SDK parsers

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.chatgptapicost.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Parameters: Temperature, Top P, and Stop

Control generation with standard parameters. temperature adjusts randomness. top_p filters nuclei sampling. stop sequences halt generation early. You can also set seed for deterministic results. These parameters give you full control over the output style.

• Temperature: Controls randomness (0.0 to 2.0)
• Top P: Nucleus sampling threshold (0.0 to 1.0)
• Stop: Array of strings to halt generation

Context window: 100,000 tokens (prompt + completion). Max output: 16,000 tokens per request.

Limits, Errors, and Context Window

Rate limits are 300 requests per minute and 8 concurrent requests per key. Request bodies must be under 8 MB. Errors include 401 for invalid keys, 402 for insufficient credit, and 429 for rate limits. Your context window is 100,000 tokens total. Errors and refusals are free.

• Rate Limit: 300 requests/minute, 8 concurrent
• Body Limit: 8 MB
• Context: 100,000 tokens (input + output)

Credit never expires. Top-up via crypto only (USDT TRC20 or USDC Base).