Quickstart for Grok users
Migrate your existing Grok API integrations to our uncensored OpenAI-compatible endpoint in minutes. This guide covers SDK configuration, streaming, tool calling, and key constraints for developers seeking a drop-in replacement.
Install the OpenAI SDK
Our API follows the standard chat-completions schema, so you can reuse the official OpenAI SDKs for Python, Node.js, and other languages. Ensure you have the latest version of your preferred client library installed. This approach lets you keep your existing application logic intact while swapping out the base URL and authentication key. You do not need a custom client or a complex routing layer. The only requirement is that your code supports standard OpenAI-compatible parameters like model, messages, and stream.
Configure Base URL and Key
Point your SDK client to our base URL: https://api.uncensoredgrok.com/v1. Set the model parameter to uncensored to access our open-weight model. Retrieve your API key from the "Get API key" page after signing up with just an email and password. No credit card is required to start. The key is displayed immediately upon signup and can be regenerated at any time, which invalidates the previous key. This simple configuration ensures your requests route correctly to our GPU servers without any hidden model routing or aggregation layers.
Send Your First Completion
Make a standard POST request to /v1/chat/completions. The model accepts text input and returns text output. It is important to note that we do not offer embeddings, image generation, audio processing, or fine-tuning endpoints. Only the chat-completions endpoint is available. Our model is tuned to answer without content refusals for lawful adult, fictional, or controversial topics. However, a hard limit always applies: requests containing sexual content involving minors are blocked. For all other lawful content, the model processes requests directly without intermediate filters.
Enable Streaming Responses
Enable streaming by setting the stream parameter to true in your request. The API returns Server-Sent Events (SSE) that you can parse token by token. This is ideal for real-time user experiences. The response format matches the standard OpenAI streaming protocol, so your existing stream parsers should work without modification. You can handle partial tokens as they arrive, reducing perceived latency for users. This feature is supported on the chat-completions endpoint and works seamlessly with both Python and Node.js SDKs.
Use Tool Calling
Function and tool calling are fully supported. You can define tools in the tools parameter and let the model decide when to call them. The response includes tool calls that you can execute in your application logic, then feed the results back into the conversation. This enables complex workflows without needing external orchestration. The model handles tool definitions and invocation transparently. Note that we do not offer model routing or multiple model choices; this single uncensored model handles all tool interactions natively.
Limits, Errors, and Context Window
Our model supports a 100,000 token context window, combining both prompt and completion tokens. The request body size limit is 8 MB. You are allowed 300 requests per minute per API key. If you receive a 401 error, your key is invalid or expired. A 402 error indicates insufficient prepaid credit. A 429 error means you have exceeded the rate limit. Pricing is transparent: $0.15 per 1M input tokens and $0.50 per 1M output tokens. Credits never expire. Check the available models endpoint to confirm the model ID is uncensored.
cURL
curl https://api.uncensoredgrok.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
}'Python
from openai import OpenAI
client = OpenAI(base_url="https://api.uncensoredgrok.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)Node.js
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.uncensoredgrok.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);Streaming
stream = 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)Specs at a glance
The numbers below are the real limits of this API, not marketing. Compare them with what your app needs.
| Feature | Support |
|---|---|
| API format | OpenAI-compatible: any OpenAI SDK or client works — change the base URL and the key |
| Base URL | https://api.uncensoredgrok.com/v1 |
| Methods | POST /v1/chat/completions · GET /v1/models |
| Model | uncensored |
| API key | Authorization: Bearer YOUR_KEY |
| Completion length | up to the rest of the 100,000-token window; max_tokens optional (no separate cap) |
| Other parameters | temperature, top_p, stop, seed and the two penalties are passed through |
| Streaming | Supported (stream: true), usage included at the end |
| Max context | 100,000 tokens (prompt + completion together) |
| Tools / tool calls | Supported: tools + tool_choice, tool_calls in the reply (streamed too), tool results as role: tool messages |
| Structured output | JSON object mode via response_format json_object |
| Requests per minute | 300/min per key |
| Request size | up to 8 MB per request |
| Headers | X-Request-Id, X-Balance-USD, X-RateLimit-Limit-Requests, X-RateLimit-Limit-Concurrency |
| Parallel requests | 8 requests at the same time per key |
| Volume bonus | +5% on $50+, +10% on $100+, +15% on $200+ |
| Price | $0.15 per 1M input tokens · $0.50 per 1M output tokens |
| Trial credit | $0.50 for 7 days, no card · Trial key: 2 parallel requests, 60 req/min; full limits (8 and 300) after first top-up |
| Top-up | crypto: USDT on TRON or USDC on Base, $20–$500, any whole sum |
| How you pay | pay as you go from prepaid credit; nothing is charged for failed or refused requests |
| Credit expiry | paid credit never expires, no subscription |
| Sign-in | sign in with Google or with e-mail + password |
| Content policy | adult content allowed; sexual content involving minors is refused |
| Keys | one key per account, regenerate any time (the old one stops working) |
Errors and what to do
Every error is JSON with a type you can switch on. You are never charged for an error.
| Code | Type | Meaning |
|---|---|---|
400 | bad_request | invalid JSON, empty messages, bad parameter, or a prompt longer than the window — fix and resend |
401 | missing_key · invalid_key · key_revoked | check the Authorization header or use your current key |
402 | no_credit | balance is empty — top up, requests resume at once |
403 | content_blocked | refused by the content policy |
404 | not_found | only /v1/chat/completions and /v1/models exist |
413 | request_too_large | request body larger than 8 MB |
429 | rate_limited · concurrency | over 300/min or 8 parallel — back off and retry |
503 | upstream_busy | model busy — retry in a few seconds |
Questions and answers
Is this the official Grok API?
No. We are an independent service. We are not OpenAI, xAI, or any other vendor. Our model is an open-weight model run on our own servers, tuned for uncensored responses. It is compatible with the Grok API format but is a distinct product.
Do you use my prompts for training?
No. Prompts sent to our API are not used for training. We focus on raw API utility. Your data privacy is maintained without requiring complex enterprise agreements.
What happens if I run out of credits?
Requests will return a 402 error until you top up your prepaid credit. You can pay by crypto (USDT or USDC) starting at $20. Credits never expire, so you can pause and resume usage at your own pace.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.