OpenAI-Compatible Endpoints
POST /v1/chat/completions works with existing OpenAI SDKs.
Uncensored LLM API
Hermes api: Uncensored LLM for Developers
Get a dedicated uncensored LLM via our openai compatible API with a 100,000 token context window and transparent prepaid token pricing.
- 100,000 token context window
- $0.15 per 1M input tokens
- Crypto top-ups only
Test with one call
curl https://api.apihermes.cc/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Generate a GET request for the user endpoint"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.apihermes.cc/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.apihermes.cc/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);per 1M input tokens$0.15
Output tokens / 1M$0.50
token context100,000
trial credit$0.50
requests per minute300
Core capabilities
Function Calling Support
Stream tools and tool_choice for complex agent workflows.
Strict JSON Output
Enable response_format json_object for reliable parsing.
Streaming via SSE
Receive real-time tokens with usage in the final chunk.
No Subscription Fees
Pay only for actual tokens used during requests.
Crypto Top-Ups Only
Fund your account with USDT or USDC easily.
Setup guide
Create Your Account
Sign up with Google or email for instant access.
Top Up with Crypto
Deposit USDT or USDC to receive bonus credit.
Start Making Requests
Use your key with the standard OpenAI Python SDK.
Common implementations
Unfiltered Content Generation
Generate adult or controversial topics without standard refusals.
Long Context Analysis
Process large documents within the 100k token window.
Roleplay Agents
Build immersive characters that stay in context longer.
Developer Testing
Test your integrations with a reliable openai compatible API.
hermes API: The Uncensored LLM API for Power Users
The hermes API delivers a single, uncensored model via OpenAI-compatible endpoints for developers who need reliable, unfiltered text generation without subscription locks.
Roleplay Agents
Send structured prompts to get consistent character voices. Function calling and JSON mode keep your agent logic clean.
Content Creation
Generate long-form drafts with a 100k context window. Streaming via SSE lets you display tokens in real time.
Research & Analysis
Process large documents without content refusals. The uncensored LLM handles controversial topics freely for lawful adult use.
Who Needs the Uncensored LLM API and Who Should Skip It
Developers building roleplay agents or content pipelines need this uncensored LLM. Power users who require function calling and streaming without subscription locks benefit from the transparent prepaid token model. Skip it if you need image generation, embeddings, or multi-model routing. This service serves one dedicated model via OpenAI-compatible endpoints. It is not a chat wrapper.
Common Mistakes When Using Uncensored LLM APIs
Developers often assume uncensored models ignore all context limits, leading to unexpected truncation during long sessions. A frequent error is ignoring the 100,000-token window, which causes silent data loss in streaming responses. Another mistake is forgetting that errors remain free, so retrying aggressively wastes compute. Some users overlook the 8MB request body limit, causing dropped requests. Always monitor token usage closely to avoid overrunning your prepaid credit unexpectedly.
H2: How our API Differs from Typical Alternatives
We offer a single, dedicated uncensored model with transparent prepaid token pricing and crypto-only top-ups, avoiding the complexity of multi-model routers.
Concrete Cost Examples with Token Arithmetic
Calculating your spend requires tracking input and output tokens separately. A single 100,000 token context window request costs $15 for input alone. Adding a modest 2,048 token response brings the total to approximately $15.01. Longer outputs scale linearly at $0.50 per million tokens. Errors consume no credit, so failed retries are free. You only pay for successfully generated text.
Checklist for Choosing an Uncensored LLM Provider
Verify the base URL is strictly OpenAI-compatible and supports streaming with function calling. Ensure pricing is transparent prepaid credit, not a subscription lock. Confirm crypto-only top-ups via USDT or USDC match your workflow. Check for 100k context windows and no hidden data training. Avoid providers routing multiple models; you need a dedicated uncensored LLM, not a generic chat wrapper.
Frequently asked questions
What is the hermes API and how does it work?
It is a hosted, OpenAI-compatible chat-completions API serving one uncensored large language model. You send text in and get text out via standard endpoints. This simple architecture ensures reliable, unfiltered responses for your applications without complex routing logic.
Does the uncensored model refuse adult content?
No, the model does not refuse lawful adult, fictional, or controversial topics. It only enforces a hard limit against sexual content involving minors. Requests of that kind are refused, but other adult themes are generated freely.
How much does the API cost per token?
Input tokens cost $0.15 per 1M tokens, while output tokens cost $0.50 per 1M tokens. Errors and refusals are free. Credit never expires, so you only pay for the actual usage of the uncensored LLM service.
Can I use the official OpenAI SDKs with this service?
Yes, the API works with official OpenAI SDKs by changing the base URL. Use HTTPS://api.apihermes.cc/v1 with your API key. Streaming, function calling, and JSON mode are all supported via standard parameters like temperature and top_p.
What are the request limits per key?
You can make 300 requests per minute with 8 concurrent requests allowed per key. The request body limit is 8 MB. Each account supports one active key, and generating a new key replaces the previous one.
Which payment methods do you accept?
Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.
Get your API key in seconds
Register, retrieve your key, and update your endpoint URL. That’s all there is to it.
