Why switch from OpenRouter?
OpenRouter is a useful aggregator, but it adds complexity when you only need one model. Routing fees and per-model pricing variations can complicate your cost calculations. Our API provides a single uncensored model with transparent, flat rates. You avoid the overhead of managing multiple provider configurations.
We charge $0.15 per 1M input tokens and $0.50 per 1M output tokens. There are no hidden routing fees or usage-based variations. Errors and refusals do not consume your credit. This simplicity makes it ideal for projects that require consistent, predictable costs without the markup of a multi-vendor platform.
Step 1: Get Your API Key
Start by creating an account using Continue with Google or an email and password. You receive an API key immediately, with no phone number verification required. This quick setup allows you to begin testing without administrative delays.
Each account allows only one active key. If you need a new key, generating one replaces the previous key. For larger projects, top-up is crypto only. We accept USDT (TRC20) or USDC (Base) in whole amounts from $20 to $500. Bonuses apply: +5% from $50, +10% from $100, and +15% from $200.
Step 2: Configure Your Base URL
Point your OpenAI-compatible SDK to our base URL: https://api.openaiapikeypricing.com/v1. This ensures all requests route to our uncensored model. You do not need to modify other parts of your client configuration.
Set your API key in the Authorization header. The standard format is Bearer YOUR_API_KEY. This works with any library that supports the OpenAI API specification. You can use this URL with Python, Node.js, or any other supported client. It simplifies integration by removing the need for custom headers or authentication logic.
Step 3: Select the Model
Use the model ID uncensored in your requests. This ID identifies our open-weight model, tuned for adult and controversial topics without refusals. It is not GPT, Claude, or any other vendor's model.
The model supports a 100,000 token context window. You can generate up to 16,000 tokens per request. If you do not set max_tokens, the limit is 2,048 tokens. This capacity handles long documents and complex conversations. You can use function calling, JSON mode, and streaming parameters.
Step 4: Send Your First Request
Send a POST request to /v1/chat/completions. Include the model ID, messages, and your desired parameters. This endpoint handles text-in, text-out interactions. It does not support embeddings, images, or audio.
Set parameters like temperature, top_p, and stop to control output. Use response_format with {"type": "json_object"} for structured data. Presence and frequency penalties are available. Errors do not consume credit. This flexibility allows you to fine-tune responses for your specific use case.
Step 5: Handle Streaming Data
Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE). Each chunk contains partial text and token usage data. The final chunk includes the total token count.
This approach reduces perceived latency for users. It allows real-time display of generated text. You can process chunks as they arrive. This is essential for chat interfaces and long-form content generation. Ensure your client handles SSE correctly to avoid connection drops.
Step 6: Monitor Usage and Costs
Track token usage via the response headers and stream chunks. Credit is charged based on real token consumption. Errors are free. Your prepaid credit never expires, so you can use it over time.
You are limited to 300 requests per minute and 8 concurrent requests per key. The request body limit is 8 MB. These limits ensure fair usage. Monitor your usage to avoid rate limits. You can check your balance and usage on the dashboard.
Step 7: Compare Pricing Models
Our pricing is straightforward: $0.15 per 1M input tokens and $0.50 per 1M output tokens. There are no monthly subscriptions or minimum spends. This contrasts with subscription services that charge for idle capacity.
You only pay for what you use. This is ideal for variable workloads. You can top up with crypto bonuses. This model reduces financial risk for developers testing new integrations.
Conclusion: Why Developers Choose Us
Developers choose this API for its simplicity and uncensored nature. You get a single model with transparent pricing. No routing fees or per-model markups. The prepaid model with no expiration fits variable budgets.
Integration is easy with standard OpenAI-compatible clients. Streaming and function calling are supported. Crypto payments with bonuses offer flexibility. Start with the trial key and scale as needed. This approach minimizes complexity and cost for NSFW and adult content projects.
