EN ▾
Get API key
Uncensored LLM API pricing guide

Quickstart for OpenAI users

Drop our uncensored LLM API into your existing OpenAI-compatible stack by swapping the base URL and API key. This quickstart covers authentication, chat completions, streaming, and tool calling with real code examples.

https://api.openaiapipricing.com/v1uncensored

Base URL and Authentication

To integrate our service, update your client configuration to point at https://api.openaiapipricing.com/v1. You can use the official OpenAI SDKs or any compatible client library by simply changing the base_url and providing your API key. Authentication relies on the standard Authorization: Bearer header. When you sign up, you receive a single key that is valid until you regenerate it. We do not require a credit card for the trial tier, but paid usage requires prepaid credits. Our openai api pricing structure is straightforward: you pay only for the tokens you consume, with no monthly subscription fees.

The model identifier you must send is uncensored. This ensures the request routes to our specific open-weight model tuned for fewer refusals. Keep your key secure, as anyone with it can consume your credits. You can regenerate your key at any time from the dashboard, which immediately invalidates the old one.

First Request

Start by sending a simple chat completion request. This confirms your authentication works and shows the model's response style. The endpoint accepts standard messages arrays with role and content fields. We support the full context window of 100,000 tokens, allowing for substantial prompt and completion lengths.

Use the following curl command to test your connection. Replace YOUR_API_KEY with the key from your dashboard.

This request will return a direct response without the usual content filters, making it ideal for creative writing, roleplay, or raw data extraction where flexibility matters.

Check the response body for the choices array containing the generated text.

curl https://api.openaiapipricing.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 SDK Integration

For Python developers, the official OpenAI SDK works out of the box with minimal changes. Import the client and configure it to use our base URL. This approach lets you leverage existing codebases with almost zero refactoring. The llm api pricing model applies equally here, so monitor your token usage to stay within budget.

Set the model name to uncensored to ensure you are hitting our specific instance. The SDK handles the JSON serialization and HTTP requests automatically. You can adjust parameters like temperature or max_tokens just as you would with other providers.

from openai import OpenAI

client = OpenAI(base_url="https://api.openaiapipricing.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 SDK Integration

Node.js developers can use the @ai-sdk/openai or the official OpenAI package. Configure the base URL to our endpoint and set the API key. This allows you to integrate our uncensored model into your Next.js or Express applications seamlessly. The token pricing remains consistent regardless of the client library used.

Initialize the client with the correct base URL. Pass the model name uncensored in your chat completion calls. This ensures compatibility with the standard OpenAI protocol while delivering our specific model behavior.

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openaiapipricing.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 Responses

Enable streaming by setting the stream parameter to true. The API returns a Server-Sent Events (SSE) stream, allowing you to process tokens as they are generated. This reduces perceived latency for end-users and is essential for real-time chat interfaces. The chat completions api supports this standard streaming format.

Parse the stream chunks to extract the delta content. This method is efficient for long outputs and provides a smoother user experience. You can stop the stream early if the user interrupts the conversation.

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)

Rate Limits and Constraints

Our infrastructure enforces a limit of 300 requests per minute per API key. If you exceed this, the API returns a 429 status code. The maximum request body size is 8 MB, which is sufficient for most large context windows. Our open ai api pricing is pay-as-you-go, so rate limits do not affect your billing directly.

If you need higher throughput, consider using multiple API keys or batching requests. Keep an eye on your token usage, as input and output tokens are priced differently. Input tokens cost $0.15 per million, while output tokens cost $0.50 per million. This pricing structure encourages efficient prompt design.

Specs at a glance

If your tool speaks the OpenAI API, these are the details that matter.

FeatureSupport
CompatibilityOpenAI-compatible: any OpenAI SDK or client works — change the base URL and the key
Model IDuncensored
EndpointsPOST /v1/chat/completions · GET /v1/models
AuthenticationBearer token in the Authorization header
Base URLhttps://api.openaiapipricing.com/v1
Completion lengthprompt + completion fit within 100,000 tokens; max_tokens optional, no separate output cap
JSON moderesponse_format: {"type": "json_object"}
Other parameterstemperature, top_p, stop, seed and the two penalties are passed through
Context window100,000 tokens (prompt + completion together)
Function callingSupported: tools + tool_choice, tool_calls in the reply (streamed too), tool results as role: tool messages
SSE streamingSupported (stream: true), usage included at the end
Response headersX-Request-Id, X-Balance-USD, X-RateLimit-Limit-Requests, X-RateLimit-Limit-Concurrency
Rate limit300/min per key
Max bodyup to 8 MB per request
Concurrency8 requests at the same time per key
PaymentUSDT (TRC20) or USDC (Base), any whole amount from $20 to $500
Subscriptionpaid credit never expires, no subscription
Volume bonus+5% on $50+, +10% on $100+, +15% on $200+
Price$0.15 per 1M input tokens · $0.50 per 1M output tokens
Free trial$0.50 for 7 days, no card · Trial key: 2 parallel requests, 60 req/min; full limits (8 and 300) after first top-up
Billingprepaid credit, charged by real token usage; errors and refusals are free
Keysone active key per account; a new key replaces the old one
Content policyadult content allowed; sexual content involving minors is refused
Sign-insign in with Google or with e-mail + password

When a request fails

The type field is stable, the message is for humans. Errors cost nothing.

StatusTypeReason
400bad_requestinvalid JSON, empty messages, bad parameter, or a prompt longer than the window — fix and resend
401missing_key · invalid_key · key_revokedcheck the Authorization header or use your current key
402no_creditbalance is empty — top up, requests resume at once
403content_blockedrefused by the content policy
404not_foundunknown endpoint
413request_too_largerequest body larger than 8 MB
429rate_limited · concurrencyover 300/min or 8 parallel — back off and retry
503upstream_busymodel busy — retry in a few seconds

Questions and answers

How do I handle authentication errors?

If you receive a 401 Unauthorized error, verify that your API key is correct and not expired. Ensure you are using the correct base URL and that the key has not been regenerated. Check that the header format is exactly Authorization: Bearer YOUR_KEY.

What happens if I run out of credits?

The API returns a 402 Payment Required error when your prepaid balance is insufficient. You must top up your account to resume service. Credits never expire, so you can add funds at your convenience without losing your previous balance.

Does the uncensored model support tool calling?

Yes, the model supports function calling within the chat completions endpoint. You can define tools in your request and the model will return structured JSON output. This allows for complex workflows and integration with external systems without leaving the chat interface.

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.