> For the complete documentation index, see [llms.txt](https://helpcenter.channable.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://helpcenter.channable.com/manage-improve-product-data/generate-with-ai/ai-generation-usage-and-costs.md).
# AI generation usage and costs
Understand token usage, generation costs, and data handling for AI generation in Channable.
Text and image generation use your [Gemini](/manage-improve-product-data/generate-with-ai/set-up-your-ai-generation-connection/how-to-create-a-gemini-connection-for-ai-generation.md) or [OpenAI](/manage-improve-product-data/generate-with-ai/set-up-your-ai-generation-connection/how-to-create-an-openai-connection-for-ai-generation.md) connection. Image generation can also use Channable's **Trial** connection.
On paid connections, charges apply when content is generated, including previews. Charges apply whether or not you approve the result. Each re-run is a new request and adds a new cost.
* [Text and image generation cost factors](#cost-factors-for-text-and-image-generation)
* [Text generation costs](#text-generation-costs)
* [Image generation costs](#image-generation-costs)
{% hint style="info" %}
#### No costs for AI-enriched attributes
[AI generated attributes](/manage-improve-product-data/generate-with-ai/ai-enriched-attributes.md) do not use Gemini or OpenAI. They do not consume provider tokens or incur provider generation costs.
{% endhint %}
{% hint style="info" %}
#### Trial image generation
The **Trial** connection for [AI generated images](/manage-improve-product-data/generate-with-ai/ai-generated-images.md) uses Channable's Gemini connection. You can generate up to five images at no cost.
{% endhint %}
***
### Cost factors for text and image generation
Your total cost depends on these factors:
* The number of items you generate content for.
* The number of previews and re-runs.
* Your provider's pricing.
Filter items before generating content. Test your setup with a small selection first.
#### Text-generation costs
Text generation uses tokens. Cost also depends on input data, prompt length, and generated-output length. Check current provider pricing before generating at scale:
* [Gemini text-generation pricing (Gemini 3.1 Flash-Lite)](https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite)
* [OpenAI text-generation pricing (OpenAI GPT-5.4 Nano)](https://developers.openai.com/api/docs/pricing)
Check **Estimated generation cost** in the **Prompting** step before generating values.
#### Image generation costs
Image generation is charged per generated image. Cost also depends on input data, prompt length, and generated-output complexity. Check current provider pricing before generating at scale:
* [Gemini image-generation pricing (Gemini 3.1 Flash Image)](https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image)
* [OpenAI image-generation pricing (gpt-image-2.5 Sunburst)](https://developers.openai.com/api/docs/pricing#image-generation)
Check **Estimated generation cost** in the **Prompting** step before generating values.
### Data use
Google and OpenAI do not use your input, prompts, or responses to improve their products. This applies when you use a paid tier or Channable's trial Gemini connection.
Read the provider terms for details: [Gemini](https://ai.google.dev/gemini-api/terms#data-use-paid) and [OpenAI](https://developers.openai.com/api/docs/guides/your-data).
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://helpcenter.channable.com/manage-improve-product-data/generate-with-ai/ai-generation-usage-and-costs.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
