API documentation

Authentication and base URL

The base URL for all requests is https://api.grokapiplatform.com/v1. Authenticate by passing your unique API key in the Authorization header. Every request must include this header to verify your account balance and apply rate limits.

Chat completions endpoint

Send text queries to POST /v1/chat/completions. The model ID to use is "uncensored". This endpoint handles standard text-in, text-out interactions without requiring extra configuration for basic usage.

Copycurl https://api.grokapiplatform.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Check my current token usage balance."}]
  }'

The model operates with a 100,000 token context window. Input and output tokens share this limit. Requests exceeding the context window will fail immediately.

Streaming responses with SSE

Enable streaming by setting stream: true in your request body. The server returns Server-Sent Events (SSE) with incremental token updates. Use this for real-time displays or to reduce perceived latency.

Copyfrom openai import OpenAI

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

Token usage details appear in the final chunk of the stream. You can track total consumption per request without parsing every intermediate delta.

Function calling and tools

Define tools in the tools array and set tool_choice to trigger specific behaviors. The model supports standard tool use patterns compatible with OpenAI SDKs.

Copyimport OpenAI from "openai";

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

Use tool_choice: "auto" for automatic selection or specify a tool name for forced execution. This works seamlessly with the uncensored model for complex reasoning tasks.

JSON mode for structured output

Set response_format to {"type": "json_object"} to enforce strict JSON output. This reduces parsing errors when integrating with frontend applications or data pipelines.

Parameters and limits

Adjust temperature, top_p, and seed to control randomness. The maximum output per request is 16,000 tokens. Errors like 401 indicate invalid keys, 402 means insufficient prepaid credit, and 429 signals rate limits. The limit is 300 requests per minute per key. Credit never expires, so you can top up with USDT or USDC whenever needed.

Streaming

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)