Your AI Drive credits are the key to unlocking advanced capabilities within our platform. You can use your credits for a variety of tasks, including OCR (Optical Character Recognition) and processing with our AI models.
Each page you process with OCR consumes one credit.
For tasks using our AI models, credit consumption varies. More sophisticated models provide deeper insights and more complex analysis, thus requiring more credits per use.Please refer to the table below for detailed credit usage per task.
Agent mode lets AI Drive plan and execute multi-step work on your behalf. Because the Agent can think for longer, use higher-power models (including Claude 4.5 Opus and GPT-5), and coordinate multiple tools, credit usage is based on the actual work performed rather than a single prompt/response.
- Model reasoning: Time spent by the selected model(s) thinking, planning, and generating results. Higher-tier models (e.g., Claude 4.5 Opus, GPT-5) consume more credits per unit of work than lighter models.
- Tools used: Each tool the Agent invokes (document reader, web fetch, data extraction, semantic search, comparison, etc.) contributes to usage based on its run time and complexity.
- Pages read: Credits scale with volume. Reading more pages across more files costs more than reading a few pages in a single file.
- Web/content retrieval: When the Agent fetches external pages or downloads files for analysis, those actions and any subsequent parsing/reading are counted.
- Parallel subtasks and retries: When the Agent branches work or retries a step to improve quality, those additional actions are included.
Chat Mode
Per-page credit charges for chat responses by model.
| Chat Model | Average Credits per Page* |
| Gemini 3 Flash Preview | 0.5 |
| Gemini 2.5 Flash | 0.5 |
| Gemini 2.0 Flash | 0.5 |
| Grok 4 Fast | 0.5 |
| Claude 4.5 Haiku | 1 |
| GPT-5 mini | 1 |
| GPT-4o mini | 1 |
| Claude 3 Haiku | 1 |
| OpenAI o3-mini | 2 |
| GPT-4.1 | 3.5 |
| Gemini 3 Pro Preview | 4 |
| OpenAI o3 | 4 |
| Gemini 2.5 Pro | 4 |
| GPT-4o | 5 |
| Claude 4.5 Sonnet | 12 |
| Claude 3.7 Sonnet | 12 |
| GPT-5.2 | 17 |
| Claude 4.5 Opus | 60 |
| OpenAI o1 | 60 |
Agent Mode Credit Usage
Agent mode tasks vary in credit consumption based on complexity, model used, and tools invoked. Here are some common examples:
| Agent Model | Cost Level |
| Claude 4.5 Opus | |
| GPT-5.2 | |
| Claude 4.5 Sonnet | |
| Gemini 3 Pro Preview | |
| Claude 4.5 Haiku | |
| Gemini 3 Flash Preview |
Example Agent Tasks
| Task | Description | Est. Credits |
| Document summarization | Read and create a comprehensive summary with key insights | 300-600 |
| Data extraction | Extract structured data from documents into tables or spreadsheets | 500-1,200 |
| Web research | Search web sources, analyze findings, and compile a report | 400-900 |
| Document review | Analyze documents, identify key points, and suggest actions | 600-1,500 |
| Multi-file analysis | Compare and analyze multiple documents, identify patterns and differences | 800-2,000 |