EN ▾
Get API key
https://api.deepseekapipricing.com/v1

DeepSeek API Pricing: Switch your client in three lines

Connect your existing client to our uncensored DeepSeek-style API by updating three configuration lines. You get a 100k context window, pay-as-you-go pricing, and no content refusals for lawful adult use.

Installation & Setup

Getting started requires zero new dependencies if you already use the standard OpenAI SDKs. The only change is the base URL pointing to our endpoint. We support POST /v1/chat/completions with streaming via Server-Sent Events (SSE) and tool/function calling. Our model ID is uncensored, an open-weight model tuned for unrestricted generation. It is not GPT, Claude, or DeepSeek, but it runs compatible code. You do not need a credit card for the initial $0.50 trial, which lasts 7 days. For production, you can top up from $20 by crypto (USDT on TRC20, USDC on Base). We charge $0.15 per 1M input tokens and $0.50 per 1M output tokens. There are no hidden tier limits or monthly fees. Your paid credit never expires. We do not offer embeddings, image generation, or fine-tuning. This is a direct text-in, text-out API. The first step is ensuring your client library is installed. If you are using Python, Node.js, or any HTTP client, the setup is minimal. You only need to configure the base URL and API key.

curl https://api.deepseekapipricing.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."}]
  }'

Base URL Configuration

Our API lives at https://api.deepseekapipricing.com/v1. This URL is compatible with any OpenAI-compatible client. You must update your client's configuration to point here instead of the default api.openai.com. The endpoint structure follows standard conventions. This allows you to swap vendors without rewriting your application logic. We support the same payload structure for chat completions. Streaming responses are available via SSE. Tool calling follows the standard function definition format. The model identifier you must send is uncensored. This tells the server which tuned model to run. It is an open-weight model hosted on our GPU servers. It does not refuse topics like other models do, except for lawful adult content involving minors. The context window is 100,000 tokens, covering both prompt and completion. This is significantly larger than many standard models. You can make up to 300 requests per minute with a single key. The maximum request body size is 8 MB. If you need to rotate your key, you can regenerate it at any time.

from openai import OpenAI

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

Authentication: API Key

Authentication is handled via the standard Authorization: Bearer <key> header. You receive your key immediately after signing up with an email and password. No phone number or credit card is required for the trial account. You can generate a new key at any time, which invalidates the old one. This is useful if you suspect a leak. We do not use your prompts for training, ensuring your data remains private. The key is tied to one account. If you share it, anyone can use your credits. For production use, you can add funds starting at $20. We offer bonuses for larger top-ups: 5% extra credit at $50 and 10% extra at $100. Your balance is visible in your dashboard. You can pay by crypto (USDT on TRC20, USDC on Base). The prepaid credit system means you only pay for what you use. There are no subscription renewals or auto-charges. If your balance hits zero, requests will fail with a 402 error until you top up. This transparency helps you control costs precisely.

import OpenAI from "openai";

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

Creating a Chat Completion

The core endpoint is POST /v1/chat/completions. You send a list of messages with roles like user or assistant. The model generates a response based on your prompt. This is where the uncensored nature shines. The model will answer controversial, adult, or technical questions without typical refusals. It is not GPT or DeepSeek, but it runs compatible code. You can specify the model as uncensored. The response includes the generated text and usage statistics. You can also enable tool calling by providing a list of functions. The model will return a function call if it determines that is the best action. This is useful for building agents or automated workflows. The context window allows for long conversations or large documents. You can send up to 8 MB of data in a single request. If you exceed the rate limit of 300 requests per minute, you will receive a 429 error. You can implement retry logic with exponential backoff. The model is hosted on our servers, ensuring low latency. We do not route between vendors. It is a single, tuned model dedicated to your requests.

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)

Streaming Responses (SSE)

For real-time applications, we support Server-Sent Events (SSE). Set stream: true in your request. The server will send chunks of text as they are generated. This provides a better user experience for chat interfaces. You can display tokens as they arrive, reducing perceived latency. The structure follows the OpenAI streaming format. Each chunk contains a delta with the generated text. You can accumulate these deltas to form the full response. This works with the Python, Node, and other SDKs. The uncensored model responds quickly, maintaining a steady stream. You do not need to wait for the entire completion. This is ideal for long-form content generation. The 100k context window means you can stream responses from large inputs. The rate limit of 300 requests per minute applies to streaming endpoints as well. If you exceed the 8 MB body limit, the stream will fail. You can handle errors gracefully by checking the status code. Streaming is supported for both standard completions and tool calls. The API key remains the same. You can regenerate it without breaking the stream if you update the client.

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)

Handling Tool/Function Calling

Tool calling allows the model to interact with external systems. Define your functions in the request. The model will return a function call object if it decides to use one. You can then execute the function and send the result back. The model continues the conversation based on the output. This is supported in our uncensored model. It is not GPT or DeepSeek, but it follows the standard format. You can define multiple functions. The model will choose the most appropriate one. This is useful for building agents that can search, calculate, or update databases. The context window supports long conversations with multiple tool calls. You can stream the response to see the function call in real-time. The rate limit applies to each request. If you make too many requests, you will get a 429 error. The model does not refuse tool calls based on content. It focuses on the task. You can test tool calling with our $0.50 trial. Claim this credit with one click on your API key page. No credit card is needed. You can top up later for production use. The API key is required for all requests.

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)

API facts in one table

The numbers below are the real limits of this API, not marketing. Compare them with what your app needs.

FeatureSupport
CompatibilityOpenAI Chat Completions schema; official openai SDKs work unchanged
AuthenticationBearer token in the Authorization header
MethodsPOST /v1/chat/completions · GET /v1/models
Base URLhttps://api.deepseekapipricing.com/v1
Modeluncensored
JSON moderesponse_format: {"type": "json_object"}
Other parameterstemperature, top_p, stop, seed and the two penalties are passed through
StreamingSupported (stream: true), usage included at the end
Completion lengthup to the rest of the 100,000-token window; max_tokens optional (no separate cap)
Function callingSupported: tools + tool_choice, tool_calls in the reply (streamed too), tool results as role: tool messages
Context window100,000 tokens, input and output combined
HeadersX-Request-Id, X-Balance-USD, X-RateLimit-Limit-Requests, X-RateLimit-Limit-Concurrency
Rate limit300/min per key
Max body8 MB request body
Concurrency8 requests at the same time per key
Top-upUSDT (TRC20) or USDC (Base), any whole amount from $20 to $500
Priceinput $0.15 / 1M tokens, output $0.50 / 1M tokens
Bonus credit+5% from $50, +10% from $100, +15% from $200
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
Credit expirypaid credit never expires, no subscription
How you paypay as you go from prepaid credit; nothing is charged for failed or refused requests
Keysone key per account, regenerate any time (the old one stops working)
Accountsign in with Google or with e-mail + password
Contentuncensored for adults; the only hard rule: no sexual content involving minors

Error codes

Every error is JSON with a type you can switch on. You are never charged for an error.

StatusTypeReason
400bad_requestmalformed request or too long for the context window
401missing_key · invalid_key · key_revokedno key, wrong key, or a key replaced by a newer one
402no_creditbalance is empty — top up, requests resume at once
403content_blockedrefused by the content policy
404not_foundonly /v1/chat/completions and /v1/models exist
413request_too_largebody over 8 MB
429rate_limited · concurrencyover 300/min or 8 parallel — back off and retry
503upstream_busymodel busy — retry in a few seconds
01

Questions and answers

What is the context window size?

Our model supports a 100,000 token context window, covering both the prompt and the completion. This allows for long conversations and large document processing. It is significantly larger than many standard models.

How do I handle rate limits?

You are limited to 300 requests per minute per API key. If you exceed this, you will receive a 429 error. You can implement retry logic with exponential backoff. The limit is per key, so you can generate multiple keys if needed.

What happens if I run out of credit?

Requests will fail with a 402 error until you top up. You can pay by crypto (USDT on TRC20, USDC on Base) starting at $20. Your prepaid credit never expires. We offer bonuses for larger top-ups.

Your key is one form away

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

Get API key