OpenAI Compatible
Works with existing SDKs by changing base_url and API key.
Uncensored LLM API
Console.mistral.api: Uncensored API Guide
Get a cheap LLM API with a 100,000 token context window and strict no-training privacy for your next project.
Claim trial keyView documentation
- Prepaid crypto billing with bonuses
- 100,000 token context window
- No training on your data
Test with a single call
curl https://api.consolemistralapi.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Return current system uptime stats in JSON format."}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.consolemistralapi.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.consolemistralapi.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);- $0.15
- per 1M input tokens
- $0.50
- Output tokens / 1M
- 100,000
- token context
- $0.50
- trial credit
- 300
- requests per minute
Core capabilities
Uncensored Model
Optimized for adult use without refusing lawful controversial topics.
Crypto Payments
Top up with USDT or USDC and receive bonus credit.
Privacy First
Prompts are never used for training your data models.
Function Calling
Supports tools, JSON mode, and streaming responses efficiently.
No Subscriptions
Pay only for tokens used with no monthly fees.
Setup guide
Create Account
Sign up with Google or email to get your key.
Add Crypto
Top up with USDT or USDC to receive bonus credit.
Start Coding
Update your base_url and send requests immediately.
Common use cases
Roleplay Generation
Generate creative stories without content filters blocking adult themes.
Code Assistance
Get coding help with a model that does not refuse.
Data Processing
Process large documents using the 100,000 token context window.
Research Models
Test LLM behaviors without standard corporate safety refusals.
What is console.mistral.api?
console.mistral.api provides an uncensored LLM endpoint for developers needing a cheap LLM API that bypasses standard refusals.
Roleplay
Generate unrestricted character dialogues without policy blocks.
Coding
Retrieve raw code outputs without unnecessary explanations.
Research
Access controversial topics directly for analysis.
When to use our uncensored API
Use this endpoint for roleplay, creative writing, or coding tasks where standard refusal filters interrupt your workflow. Our model answers without blocking lawful adult or controversial topics, ensuring you receive the full output you requested. It integrates seamlessly with existing OpenAI SDKs, so you can swap the base URL without rewriting client code. This is ideal for developers needing a cheap LLM API that prioritizes output over moderation, though it lacks embeddings or image generation features.
Developer questions about usage
Developer questions about usage
Verify your integration by monitoring request headers and response payloads directly, not just the provider console.
- Check your base URL matches
https://api.consolemistralapi.com/v1exactly. - Ensure you send the model ID as
uncensoredin yourchat.completionspayload. - Confirm streaming works via SSE, noting token counts appear in the final chunk.
Our API requires a specific key configuration distinct from standard vendors.
Common billing mistakes to avoid
Prevent overcharges by respecting the 16,000 token output ceiling and the $0.50 per 1M output token rate.
- Set
max_tokensexplicitly to avoid unexpected costs if the model generates excessively long responses. - Remember that errors are free, but successful completions charge for every token sent back.
- Keep request bodies under 8 MB to ensure smooth processing without hidden fees.
Real token cost examples
Calculate your exact spend before sending requests. Input tokens cost $0.15 per million, while output tokens cost $0.50 per million. A 10,000-token prompt with 1,000 output tokens uses 11,000 total tokens. This totals $0.00165. Errors are free. Prepaid credit never expires. Check the billing page for live rates.
How we differ from standard providers
We use prepaid token billing without monthly subscriptions. You top up with USDT or USDC and get bonus credit. We do not train on your prompts. Our API serves one uncensored model via the standard OpenAI-compatible endpoint. There are no hidden fees for errors.
| Feature | Our API | Standard Providers |
|---|---|---|
| Billing | Prepaid tokens | Monthly plans |
| Privacy | No training | Variable |
| Model | Uncensored | Filtered |
Frequently asked questions
What is console.mistral.api and how does it work?
It is an independent, uncensored LLM service. You send requests to HTTPS://api.consolemistralapi.com/v1. The endpoint accepts standard chat-completions payloads. It returns text responses without content refusals. This setup works with any OpenAI-compatible SDK. You can use the exact same client code.
Does the uncensored model refuse adult content?
No, it rarely refuses lawful adult topics. It allows fictional and controversial narratives. Only sexual content involving minors is strictly blocked. The model answers directly without extra moralizing. You get consistent output for creative writing. This makes it ideal for roleplay tasks.
How much does the API cost per token?
Input tokens cost $0.15 per million tokens. Output tokens cost $0.50 per million tokens. Errors and refusals do not consume credit. You pay only for actual usage. There are no monthly subscriptions. You can top up using crypto only.
Can I use this with Python or Node.js?
Yes, it is fully OpenAI-compatible. You just change the base URL in your SDK. The endpoint accepts standard chat-completions JSON. You send the model id as uncensored. Streaming and function calling work normally. The code remains identical to standard implementations.
What is the maximum context window size?
The context window supports 100,000 tokens total. This includes both the prompt and the completion. You can generate up to 16,000 tokens per request. If you do not set max_tokens, the limit is 2,048 tokens. This allows processing large documents efficiently.
How do I pay for the service?
You pay via prepaid credit using crypto only. Accepted currencies are USDT on TRC20 or USDC on Base. Minimum top-ups start at twenty dollars. Bonuses range from five to fifteen percent. Credits never expire.
Secure your API key
Register, retrieve the token, and update your endpoint. Simple.
