How much does the AI cost?
What is BYOK?
BYOK stands for “bring your own key”. Novelcrafter is designed firstly as a writing platform, and we don’t want to tie you down with limited LLM models. You can connect local models that run off your own computers (and are therefore ‘free’, save your energy bill), or via vendors like OpenRouter or OpenAI, and featherless.
This flexibility means that no matter what your price point is, you can still write.
Please look up the pricing structure of the vendor for the model you are trying to run. here are the links to the popular vendors we support:
Example Model Costs
Here are example costs of some models,
For a full list of the model costs that OpenRouter provide, see here. All figures are correct as of November 2024.
Input cost: the cost per 1000 tokens in your prompt
Output cost: the cost per 1000 tokens in the output of the AI.
All prices are in USD.
Example Prompt
The following assumptions will be made for our hypothetical generation (a beat to prose prompt used in the write interface):
Input
- We have used the system general purpose prompt, with 1,982 words of prose before being read.
- We have called 9 codex entries, with a combined word count of 643 words.
- 367 words of chapter summaries has been included.
Output
- We have an output of 400 words = around 500 tokens
Of course, your prompt input and output will differ, depending on how large your codex is, the amount of prose/outline in the context, and the output.
This is a good approximation for us to work with, however.
High-cost
| Model | Input Cost | Output Cost | Example Prompt Cost |
|---|---|---|---|
| Claude Opus | 0.015 | 0.075 | 0.1005 |
| GPT4 (non-turbo, 32k) | 0.06 | 0.12 | 0.3100 |
| GPT4-turbo | 0.01 | 0.03 | 0.0550 |
Input and output cost measured per 1k tokens, all prices in USD.
Mid-cost
| Model | Input Cost | Output Cost | Example Prompt Cost |
|---|---|---|---|
| GPT3.5-turbo | 0.003 | 0.004 | 0.0145 |
| GPT4o | 0.005 | 0.015 | 0.0275 |
| Claude 3.5 Sonnet | 0.003 | 0.015 | 0.0200 |
| Mistral Large | 0.002 | 0.006 | 0.0113 |
| Mistral Medium | 0.0027 | 0.008 | 0.0153 |
Input and output cost measured per 1k tokens, all prices in USD.
Low-cost
| Model | Input Cost | Output Cost | Example Prompt Cost |
|---|---|---|---|
| Claude 3 Haiku | 0.00025 | 0.00125 | 0.0016 |
| Claude 3.5 Haiku | 0.001 | 0.005 | 0.0067 |
| Weaver | 0.001875 | 0.00225 | 0.0896 |
| Gemini Pro 1.5 | 0.0025 | 0.0075 | |
| Airoboros | 0.0005 | 0.0005 | 0.0023 |
| 4o mini | 0.00015 | 0.0006 | 0.00093 |
Input and output cost measured per 1k tokens, all prices in USD.
Free (As of November 2024)
These are based on OpenRouter prices. Locally run models are of course all free too (see below).
- Google Gemma 2 9B
- Meta Llama 3 8B instruct
- Google Gemini Flash 8B Experimental
- Nous Hermes
- Mythomist 7B
- Toppy
- Hugging Face Zephyr 7B
Running Local Models
Another alternative is to run a local model using a provider such as LM Studio and Ollama. This will cost electricity, and will be limited to how powerful your computer is, however it is worth looking into if you want to use one of the open-source models.
Fixed Rate
We now support connections to featherlessAI, infermatic, and Arli AI for those of you who want unlimited AI use with a monthly fee, rather than pay-as-you-go.