Integrate the Cheapest LLM API in Minutes

Install the Standard SDK

Start by installing the official library for your preferred language. This ensures you get the latest OpenAI-compatible features without writing custom HTTP clients. You can use pip for Python or npm for Node.js to get set up quickly.

Configure Base URL and Key

Point your SDK to our base URL and set your API key. This single configuration change allows you to swap in our service without rewriting your application logic. You get a key immediately after signing up with Google or email.

The base URL is https://api.apillmcheapest.com/v1. Authentication uses a standard Bearer token. The API key is generated instantly upon account creation via the Get API key page.

Base URL: Set the base_url to https://api.apillmcheapest.com/v1 in your SDK configuration.

No Minimum Spend: You only pay for tokens used. There are no monthly fees or subscriptions.

Send Your First Completion

Make a POST request to /v1/chat/completions with the model ID uncensored. This model is open-weight and tuned to answer without content refusals for lawful adult use. It is not GPT, Claude, or any other vendor's model.

The API accepts standard parameters like temperature, top_p, and stop. You can specify response_format for JSON mode. The context window supports up to 100,000 tokens for prompt and completion combined.

Example:

Copycurl https://api.apillmcheapest.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "What is the current status of the database migration job?"}]
  }'

Response: You receive a text response or JSON object. Errors like 401 (invalid key) or 402 (no credit) are returned clearly. Refusals are free, so you only pay for actual usage.

Enable Streaming for Real-Time Output

Enable streaming by setting stream: true in your request. The API returns tokens via Server-Sent Events (SSE). Token usage is reported in the last chunk of the stream.

This is ideal for chat interfaces or real-time analysis. You can process tokens as they arrive, reducing perceived latency for your users. The model supports streaming natively.

Example:

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)

Usage: Monitor the final chunk for token counts. This helps you track costs accurately without waiting for the full response.

Use Function Calling and JSON Mode

Support function calling with the tools and tool_choice parameters. You can also enforce strict JSON output using response_format: {"type": "json_object"}. This is useful for extracting structured data from text.

The model supports parameters like temperature, top_p, stop, seed, presence_penalty, and frequency_penalty. These allow fine-tuning of the output style and randomness.

Example:

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.apillmcheapest.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);

Limit: Max output is 16,000 tokens per request. If max_tokens is not set, it defaults to 2,048.

Limits, Errors, and Context Window

The API has a context window of 100,000 tokens. You can send up to 300 requests per minute and 8 concurrent requests per key. The request body limit is 8 MB.

Errors: 401 indicates an invalid key. 402 means no credit. 429 is a rate limit. Refusals are free, so you only pay for successful or failed but counted tokens.

Credit: Prepaid credit is charged by real token usage. Paid credit never expires. Top-up is crypto only (USDT TRC20 or USDC Base). Bonuses: +5% from $50, +10% from $100, +15% from $200.

Keys: One active key per account. A new key replaces the old one. No phone number required for signup.

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.apillmcheapest.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)