Pricing and billing
What you pay for
- Prompt + key: a one-time purchase of a model's prompt. A $2 gift lands on your balance together with the key.
- Another key for the same model: the extra-key price, without paying for the prompt again.
- Requests: by tokens, with separate input and output prices for each model.
- .txt + guide: the prompt as a file, a separate purchase.
| Model | model ID | Input, 1M tokens | Output, 1M tokens |
|---|---|---|---|
| DeepSeek | deepseek | $0.30 | $1.20 |
| Kimi | kimi | $0.30 | $1.20 |
| GLM | glm | $0.30 | $1.20 |
| Gemini | gemini | $0.30 | $1.20 |
How a request is priced
cost = input tokens × input price / 1,000,000
+ output tokens × output price / 1,000,000The amount is rounded up to $0.000001. Input tokens include the model's built-in prompt.
When money is charged
Right after the model replies. Every request with its tokens and cost appears in the console under “Usage”, and you can export it to CSV.
Requests that fail on our side are not billed.
When the balance runs out
The API returns 402 insufficient_balance and the bot sends a notice. Keys start working again as soon as you top up.