Kimicode: What it costs
Kimicode charges strictly for tokens used, ensuring you pay only for the work that succeeds. Errors and refusals are free, so your prepaid balance is never drained by retry loops or content filters.
- per 1M input tokens
- $0.15
- Output tokens / 1M
- $0.50
- token context
- 100,000
- trial credit
- $0.50
- requests per minute
- 300
Top-ups from $20 to $500, any whole amount. Bonus credit: +5% from $50, +10% from $100, +15% from $200.
Cost calculator
Worked examples
Bulk content translation
Translating a 2,000-token English document into Spanish typically generates 2,100 tokens. Cost: (2,000 / 1,000,000 * $0.15) + (2,100 / 1,000,000 * $0.50) = $0.0003 + $0.00105 = $0.00135.
Long-form creative writing
A prompt with 50,000 tokens of context generates a 5,000-token story. Cost: (50,000 / 1,000,000 * $0.15) + (5,000 / 1,000,000 * $0.50) = $0.0075 + $0.0025 = $0.01.
Code generation with retry
An API call fails due to a transient error, costing $0.00. A subsequent successful call uses 10,000 input tokens and 800 output tokens. Cost: (10,000 / 1,000,000 * $0.15) + (800 / 1,000,000 * $0.50) = $0.0015 + $0.0004 = $0.0019.
Token Usage Rates
Kimicode applies a straightforward tiered rate for text generation. Input tokens are billed at $0.15 per million tokens, while output tokens are billed at $0.50 per million tokens. This structure reflects the higher compute cost of model inference during generation compared to processing your prompt.
Because Kimicode serves a single uncensored model, you avoid the variable pricing often found in model routing services. You know exactly what a million tokens cost regardless of the underlying hardware. All tokens—both from your request and the model's response—are tallied in the API response headers, providing full transparency on every billable event.
Prepaid Credit Model
Our billing is entirely prepaid. You load credit into your account, and tokens are deducted as they are consumed. This model eliminates the risk of surprise invoices or credit card charges after a high-volume burst. Crucially, errors are free. If the API returns a 500 error or times out, those tokens are not deducted from your balance. This makes Kimicode ideal for automated pipelines where retry logic is common, as you only pay for successful completions.
Your credit never expires, so you can top up once and use the balance over months or years without penalty. There are no monthly subscription fees or minimum spend requirements.
Crypto Top-Up & Bonuses
Top-ups are processed by crypto (USDT on TRC20, USDC on Base) to keep overhead low and transactions global. For crypto we accept USDT (TRC20) and USDC (Base). You can top up any whole amount between $20 and $500 per transaction. There are no hidden network fees deducted from your credit; the full amount you send is credited to your account.
We reward larger deposits with bonus credit. Top-ups of $50 or more receive a +5% bonus, and top-ups of $100 or more receive a +10% bonus. This bonus is applied immediately to your available balance, giving you more tokens for your investment.
What your credit buys
No tiers: every key gets the full feature set and the same limits.
| Feature | Support |
|---|---|
| Structured output | response_format: {"type": "json_object"} |
| Tools / tool calls | Yes — tools, tool_choice; replies carry tool_calls, also when streaming; send results back as role: tool |
| Context window | 100,000 tokens (prompt + completion together) |
| Completion length | prompt + completion fit within 100,000 tokens; max_tokens optional, no separate output cap |
| Requests per minute | 300/min per key |
| Parallel requests | up to 8 in parallel per key |
| Trial credit | $0.50 for 7 days, no card · Trial key: 2 parallel requests, 60 req/min; full limits (8 and 300) after first top-up |
| Top-up | USDT (TRC20) or USDC (Base), any whole amount from $20 to $500 |
| Token prices | input $0.15 / 1M tokens, output $0.50 / 1M tokens |
| Volume bonus | +5% on $50+, +10% on $100+, +15% on $200+ |
| Subscription | paid credit never expires, no subscription |
Questions and answers
Do I get charged if the model refuses a prompt?
Yes. If the model processes your request and returns a refusal (e.g., due to the hard content limit), those tokens are billed. Only network errors or server failures result in free tokens.
What happens to my unused credit?
Your credit never expires. You can leave a balance in your account indefinitely and add more later. There are no dormancy fees or expiration dates.
Can I get a refund if I top up too much?
Credit is generally non-refundable. However, if you experience a double charge or a technical error during top-up, you can request a correction via the Support page.
How does the trial credit work?
New accounts receive $0.50 in trial credit valid for 7 days. Claim this credit with one click on your API key page. No credit card is needed. The trial credit is used on a first-come, first-served basis and cannot be withdrawn.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
