Uncensored API Pricing & Top-Up

We bill strictly for what you use with transparent prepaid credit, so your uncensored LLM costs stay predictable without monthly fees. This cheap LLM API alternative to expensive vendor APIs charges $0.15 per 1M input tokens and $0.50 per 1M output tokens.

per 1M input tokens: $0.15
Output tokens / 1M: $0.50
token context: 100,000
trial credit: $0.50
requests per minute: 300

Reference scenarios

Standard chat completion with moderate context

If you send a 50,000 token prompt and receive a 2,000 token response, you pay for 50,000 input tokens ($0.0075) and 2,000 output tokens ($0.001). The total cost for this single request is $0.0085.

Long-form content generation with high output

When generating a 10,000 token response from a 10,000 token prompt, the input cost is $0.0015 and the output cost is $0.005. You spend exactly $0.0065 for that completed generation.

Heavy streaming session with token overhead

A streaming session using 100,000 input tokens and 8,000 output tokens costs $0.015 for input and $0.004 for output. The total charge is $0.019, demonstrating how prepaid credit scales with volume.

Transparent Token Pricing

We charge only for actual token usage, not for API calls or idle time. This approach ensures you pay a cheap LLM API rate that reflects real consumption. Errors and refusals do not consume your balance, so you never pay for failed attempts. The cost calculation is straightforward: input tokens are billed at $0.15 per million, while output tokens cost $0.50 per million. This structure aligns with standard OpenAI API pricing models, making migration easy for developers already familiar with those rates. You can track your exact spend in real-time as tokens are processed.

curl https://api.ollamaopenaiapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list open ports on this server"}]
  }'

Prepaid Credit & No Expiration

Your prepaid credit never expires, allowing you to top up once and use the uncensored LLM service indefinitely. There are no monthly subscriptions or hidden fees to manage, which simplifies budgeting for long-term projects. Since credit is charged by real token usage, you only spend what you actually consume. This model eliminates the risk of paying for unused capacity or forgetting to cancel a recurring plan. You maintain full control over your spending limits by managing your own credit balance directly.

from openai import OpenAI

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

Why Prepaid Keeps Spend Predictable

A prepaid balance prevents surprise bills from runaway streaming sessions or unexpected token spikes. You can set a hard limit on your spending by topping up with a specific amount. This is crucial for developers running continuous background jobs or automated workflows where token counts might fluctuate. Unlike subscription models that charge for availability regardless of use, prepaid credit ensures every dollar spent results in actual model output. You can easily estimate your costs using our calculator before making a top-up.

import OpenAI from "openai";

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

Common questions

Does the prepaid credit expire?

No, your prepaid credit never expires. You can top up once and use the funds whenever you need them, with no time pressure to consume the balance. This makes it ideal for long-term development cycles where usage might be intermittent.

Do errors or refusals cost credit?

Errors and refusals are free, meaning you only pay for successful token generation and input processing. If a request fails due to a network issue or exceeds a limit without consuming tokens, you are not charged. This ensures your balance is spent only on actual work done by the model.

How do I know my exact costs?

You can view your usage and exact costs in your account dashboard, which breaks down input and output tokens. The pricing is transparent: $0.15 per 1M input tokens and $0.50 per 1M output tokens. You can also use our cost calculator to estimate expenses before sending requests.

Is there a minimum top-up amount?

The minimum top-up amount is $20 when using crypto. You can top up any whole amount between $20 and $500, with bonus credits applied for larger amounts. This flexibility allows you to start small and scale your credit as your usage grows.

Secure your API key

Claim trial key