OpenAI API Alternative: Token pricing
Drop-in uncensored OpenAI API alternative
Understand exactly what you pay for with our transparent, per-token pricing model. No hidden fees, no tiered surprises—just straightforward costs for every request.
No subscription. Prepaid credit never expires.
- per 1M input tokens
- $0.25
- Output tokens / 1M
- $1.00
- token context
- 64,000
- trial credit
- $0.50
- requests per minute
- 300
Cost calculator
Worked examples
A developer running an automated code-review bot that processes 100,000 input tokens and generates 5,000 output tokens per day.
Daily cost: (100,000 / 1,000,000 * $0.25) + (5,000 / 1,000,000 * $1.00) = $0.025 + $0.005 = $0.03. Monthly estimate: ~$0.90.
An AI agent performing deep research by reading a 30,000-token document and summarizing it into a 1,000-token report.
Cost: (30,000 / 1,000,000 * $0.25) + (1,000 / 1,000,000 * $1.00) = $0.0075 + $0.001 = $0.0085 per request.
A chatbot handling a 2,000-token conversation history and generating a 500-token response.
Cost: (2,000 / 1,000,000 * $0.25) + (500 / 1,000,000 * $1.00) = $0.0005 + $0.0005 = $0.001 per interaction.
Pay-As-You-Go Prepaid Credit
Our llm api operates on a prepaid credit system. You load funds into your account, and we deduct costs based on token usage. There are no monthly subscriptions or recurring fees. This model ensures that your spending is strictly tied to actual consumption, making it ideal for developers who want precise control over their ai chat api budget. Unused credit does not expire, allowing you to pause and resume usage without penalty. This approach eliminates the risk of overages common in subscription-based models, giving you complete visibility into your costs.
Trial Credit for Testing
New accounts receive $0.50 in trial credit, valid for 7 days. No credit card or phone number is required to start. This allows you to test the serverless llm performance and verify integration with your existing SDKs. Once the trial credit is exhausted or expires, you can top up to continue using the service. The trial provides a realistic sample of input/output token ratios, helping you estimate long-term costs before committing funds. It is a single-use benefit per person, designed to remove friction from the onboarding process.
Predictable Spending with Prepaid Balance
Using a prepaid balance ensures that your usage can never exceed the amount you have loaded. This is critical for managing budgets in production environments where traffic spikes might occur. Unlike credit card models that might incur unexpected overages, our system stops processing requests once the balance is depleted. This predictability extends to every uncensored llm api call, allowing you to forecast expenses accurately. You can also regenerate your API key without affecting your balance or rate limits, providing flexibility in key management.
Questions and answers
Does regenerating my API key reset my rate limits?
No, rate limits are tied to your account, not the specific key. Regenerating your key revokes the old one but keeps your usage history and limits intact.
How does the 8 MB request body limit affect token usage?
The 8 MB limit applies to the total request size, not just tokens. For most standard text inputs, this allows for very large context windows, well beyond the 64k token limit of our model.
Are there any hidden fees for streaming or tool calling?
No. Streaming via SSE and tool/function calling are included at the standard token rates. You only pay for the input and output tokens processed.
What happens if I don't use my trial credit within 7 days?
The trial credit expires after 7 days and is not replenished. You will need to add prepaid credit to continue using the API after the trial period ends.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
