OpenAI-Compatible Endpoints
Use the standard /v1/chat/completions endpoint with streaming and tool/function calling support. Your existing client code works by simply updating the base_url and API key.
Chinese LLM APIUncensored LLM via OpenAI-compatible API
Get API keyUncensored & OpenAI-Compatible
A dedicated API for an uncensored LLM, accessible via standard OpenAI SDKs without content filters or training data usage.
curl https://api.chinesellmapi.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."}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.chinesellmapi.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)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.chinesellmapi.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 the standard /v1/chat/completions endpoint with streaming and tool/function calling support. Your existing client code works by simply updating the base_url and API key.
Pay-as-you-go prepaid credit with no monthly fees. Costs are $0.15 per 1M input tokens and $0.50 per 1M output tokens, with bonus credits for larger top-ups.
Process large inputs with a 100,000 token context window (prompt + completion). This supports extensive document analysis and long-form generation in a single request.
Prompts are not used for training your model data. We require only an email and password to sign up, keeping your identity minimal and secure.
One uncensored model, served directly with no routing between vendors. This provides consistent performance without the latency or filtering layers of proxy services.
Access is capped at 300 requests per minute per key and an 8 MB request body. You can regenerate your API key instantly if needed, revoking the old one.
Register with an email and password to receive your API key immediately.
Update your OpenAI SDK configuration to point to our base URL and insert your key.
Start sending chat completions and receive uncensored text outputs directly.
Generate stories and scripts without unwanted moralizing or content filters interrupting the narrative flow. Ideal for adult-themed fiction or bold creative directions.
Query the model for vulnerability details or controversial technical topics without refusals based on common safety training. Useful for red-teaming or detailed technical analysis.
Process large documents with the 100k context window to extract structured data or summaries. The uncensored nature ensures the model does not refuse based on content type.
Build chatbots that respond naturally to a wide range of user prompts. Tool calling support allows for function execution alongside text generation.
Many developers seek an uncensored deepseek or similar model but find that US-based providers apply strict content filters. Our API serves one uncensored model that answers without refusals for lawful adult use, controversial topics, or security research. We are not a proxy; we serve one model directly, ensuring direct access without the latency of routing between vendors.
This is not for users needing multiple models, image generation, or embeddings. It is for developers who want a single, unrestricted text model accessible via standard OpenAI SDKs. The model is not GPT, Claude, Gemini or Grok, but it follows the same API contract.
We expose standard endpoints: POST /v1/chat/completions and GET /v1/models. Streaming via SSE and tool/function calling are supported. You send text, you get text. There are no embeddings, audio, video, or fine-tuning endpoints. The model ID to send is "uncensored".
from openai import OpenAI
client = OpenAI(base_url="https://api.chinesellmapi.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)Configure your client with base_url="https://api.chinesellmapi.com/v1" and your API key. The rest of your code remains identical to standard OpenAI integrations. This approach minimizes friction for teams already using OpenAI-compatible clients.
We use a transparent per-token pricing model with no subscriptions. Input tokens cost $0.15 per 1M, and output tokens cost $0.50 per 1M. You can top up with a minimum of $20 by crypto (USDT on TRC20, USDC on Base). Larger top-ups include bonus credits: +5% from $50, +10% from $100, +15% from $200.
Paid credit never expires. We do not offer a free unlimited tier; every request consumes tokens. This model is ideal for variable workloads where you only pay for what you use.
curl https://api.chinesellmapi.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."}]
}'Check the pricing page for detailed breakdowns of token costs.
The API supports a 100,000 token context window, combining both prompt and completion tokens. This allows for extensive document processing and long-context interactions in a single request. Tool calling is fully supported, enabling the model to execute functions or return structured data.
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)Requests are limited to 8 MB in body size and 300 requests per minute per key. If you need higher throughput, you can generate additional keys, though each account is limited to one active key at a time unless regenerated.
Your prompts are not used for training. We require only an email and password to create an account, and no phone number or credit card is needed for the trial. We do not track your usage for marketing purposes, and we do not claim to track it either; we simply do not use your data for training the model.
Content filtering is minimal: the only hard limit is that requests involving sexual content with minors are always blocked. All other lawful adult, fictional, or controversial content is allowed. This ensures privacy while maintaining basic safety standards.
New accounts receive $0.50 in trial credit valid for 7 days. Claim this credit with one click on your API key page. No card is required to start. This allows you to test the API, verify streaming, and check tool calling before committing to paid credit. The trial is one per person.
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.chinesellmapi.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);Sign up on the "Get API key" page to receive your key immediately. You can regenerate your key at any time, which revokes the old one. This is a simple, direct path to an uncensored LLM without complex setup.
We don't disclose the underlying base model. You get one uncensored model behind an OpenAI-compatible API, with model id uncensored, 100k context and the same behaviour on every request.
We serve one uncensored model directly, with no routing between vendors. This provides direct access with transparent pricing and no intermediary filtering layers. Proxy services often add latency and may retain data.
No, prompts are not used for training. We do not track your usage for marketing purposes, and we do not claim to track it either. Your data remains private and is not used to improve the model.
Yes, it is fully OpenAI-compatible. You only need to update the base_url to https://api.chinesellmapi.com/v1 and set your API key. The rest of your code works as expected.
You are limited to 300 requests per minute per key and an 8 MB request body. Each account has one key, which can be regenerated at any time to revoke the old one.
Create an account, copy the key, change the base URL. That is the whole setup.
Practical articles on setup, pricing and integration.
OpenRouter Alternative for Chinese-Language AppsAn OpenRouter alternative for Chinese apps: one hosted model versus a router, who each suits, a side-by-side test script and a worked monthly cost.
Cheap Chinese LLM API: What to Compare Beyond PriceHow to pick a cheap Chinese LLM API: measure tokens on real Chinese text, compare input and output rates, context and limits. Our rates are a…
OpenAI Compatible API URL: Base URL and HeadersThe exact OpenAI compatible API URL for Chinese LLM API, plus headers, SDK settings, env vars and fixes for the 404 and 401 errors people hit most…
Building a Chinese-language app: prompts, script control and UTF-8Start with our Chinese LLM API. Control Simplified or Traditional output, handle UTF-8, and manage token budgets. Get started now.
Chinese LLM API free trial: how it works and what people askGet a Chinese LLM API free trial with $0.50 credit. No payment details needed. Explore limits, error codes, and content rules. Start now.
Chinese↔English translation and localization through a chat APIUse our Chinese LLM API for translation with glossaries and placeholders. Get accurate results via JSON. Try it now.