EN ▾
Uncensored LLM API starting at $0.15 per 1M tokenshttps://api.cheapllmapis.com/v1

Simple, Cheap LLM API Pricing

Stop paying for model routing you don't need. Our pay-as-you-go llm pricing starts at $0.15 per 1M input tokens with zero monthly fees, so you only pay for the text you generate.

Top-ups from $20 to $500, any whole amount. Bonus credit: +5% from $50, +10% from $100, +15% from $200.

No subscription. Prepaid credit never expires.

Get API keyRead the docs

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

Cost calculator

$0.00

Worked examples

  1. Long-form uncensored story generation

    A developer generates a 20,000-token story. Input: 2,000 tokens ($0.0005). Output: 18,000 tokens ($0.018). Total cost: $0.0185. This demonstrates the low cost of our cheap llm api for creative writing tasks without subscription overhead.

  2. High-volume chat completions

    An app processes 100,000 short user messages. Input: 50,000 tokens ($0.0125). Output: 50,000 tokens ($0.05). Total cost: $0.0625. The pay as you go llm model scales linearly with usage.

  3. Technical documentation summarization

    Summarizing a large codebase. Input: 50,000 tokens ($0.0125). Output: 5,000 tokens ($0.005). Total cost: $0.0175. Precise input/output tracking ensures you know exactly what you spend.

Usage-Based Pricing

Our llm api pricing is straightforward: you pay only for the tokens you consume. Input tokens cost $0.15 per million, and output tokens cost $0.50 per million. This transparent pricing structure allows developers to forecast costs accurately without hidden fees.

Unlike competitors that bundle expensive model routing, we offer a single highly optimized uncensored model. This keeps costs low because you aren't paying for a marketplace of models you don't use. You can switch from OpenAI's standard rates to our cheaper rates immediately.

The price per token remains constant regardless of volume. Whether you send one request or one million, the rate stays the same. This consistency is vital for hobbyists and small teams who need predictable billing.

No Monthly Fees or Minimum Spend

We believe in a no minimum spend llm model that respects your budget. There are no monthly subscriptions, no base fees, and no auto-renewals. If you don't use the API, you don't pay anything. This is ideal for intermittent projects or testing phases.

Your prepaid credit never expires, so you can top up once and use it over weeks or months. This flexibility means you aren't forced to burn through credits before a deadline. You can pause usage without losing your balance.

Developer simplicity is our priority. You load funds, get an API key, and start sending requests. There is no enterprise contract to sign or minimum commitment to worry about. It is pure pay-as-you-go utility.

Top-Up Bonus Credits

To reward consistent usage, we offer bonus credits on larger top-ups. When you add $50, you receive a 5% bonus. Adding $100 grants a 10% bonus. These extra credits extend your usage without increasing your initial spend.

Bonus credits are applied instantly to your balance. They are used alongside your base credits for all requests. This means your effective cost per token drops further as you load more funds. It is a direct discount on our already low prices.

You can top up by crypto (USDT on TRC20, USDC on Base). The process is instant, and the bonus is reflected in your dashboard immediately. This feature makes our cheap chatgpt api alternative even more attractive for high-volume users.

Questions and answers

How does prepaid credit work?

You load funds into your account, and the balance is deducted in real-time as tokens are processed. Usage can never exceed what was loaded, keeping your spend predictable. Credits do not expire, so you can use them whenever you are ready.

Do I need a credit card for the trial?

No. The $0.50 trial credit requires only an email and password. Claim this credit with one click on your API key page. No card is needed, and no phone number is required. The trial is valid for 7 days, giving you enough time to test the uncensored model thoroughly.

Can I mix input and output tokens?

Yes. Each request counts both input and output tokens separately. Input tokens are billed at $0.15 per million, and output tokens at $0.50 per million. The total cost is the sum of both components.

What happens if I run out of credits?

Requests will fail until you add more funds. You can top up at any time by crypto (USDT on TRC20, USDC on Base). There is no penalty for running out, and your balance will not expire. You can resume usage immediately after topping up.

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.

Get API keyRead the docs

Plan details

No tiers: every key gets the full feature set and the same limits.

FeatureSupport
Completion lengthprompt + completion fit within 100,000 tokens; max_tokens optional, no separate output cap
JSON moderesponse_format: {"type": "json_object"}
Context window100,000 tokens (prompt + completion together)
Tools / tool callsSupported: tools + tool_choice, tool_calls in the reply (streamed too), tool results as role: tool messages
Rate limit300 requests per minute per key
Parallel requests8 requests at the same time per key
Trial credit$0.50 of credit valid 7 days, no card needed · Trial key: 2 parallel requests, 60 req/min; full limits (8 and 300) after first top-up
Token pricesinput $0.15 / 1M tokens, output $0.50 / 1M tokens
Paymentcrypto: USDT on TRON or USDC on Base, $20–$500, any whole sum
Credit expiryno monthly fee; paid credit does not expire
Bonus credit+5% on $50+, +10% on $100+, +15% on $200+

The complete technical table is in the documentation.