Work with AI data
Once you've imported your AI data into the DoiT platform, you can start analyzing and monitoring your AI cost and usage. AI data is tracked and reported on an hourly basis.
AI API
The DoiT console interacts with the following AI APIs:
| AI tool | Description |
|---|---|
| OpenAI | |
| Anthropic | Anthropic Costs and Usage API endpoint. |
The required permissions are granted when you connect your AI tools to the DoiT platform.
AI data in Cloud Analytics
You can get AI data through dimensions and metrics. See below for the mapping between the DoiT and AI terminologies.
Basic metrics
DoiT term | AI term | AI definition |
|---|---|---|
cost | cost | The total cost for a specific resource or usage. |
usage | usage | The usage for tokens. In addition, the usage metric includes consumption based on seconds, bytes, characters, and so on, depending on the specific service, model, or operation being tracked. |
Standard dimensions
You can get AI data through the standard Cloud Analytics dimensions. The table below explains the standard dimensions that are available for all AI models that are integrated with the DoiT platform.
| DoiT term | Description |
|---|---|
| Billing Account | The unique identifier for a specific organization in your AI account. |
| Project ID/Account ID | The unique identifier for your OpenAI project or Anthropic workspace. |
| Service ID/Service Description/SKU Description | The high-level description of the type of product or capability that you are using. OpenAI examples include Completions API,Embeddings API. Anthropic examples include Claude haiku3.5 Usage - Input tokens, Web Search Usage. |
| SKU ID/SKU description | The specific, granular and billable unit within the service that you are using. OpenAI examples include chatgpt-4o-latest, input, text-embedding-3-large. Anthropic examples include claude-3-5-haiku-20241022, input_tokens, claude-sonnet-4-20250514, output_tokens`. |
| Usage | The primary unit of usage. For both Anthropic and OpenAI the primary unit is the token, but they also use other units depending on the service you are consuming. |
| Operation | A distinct, billable action of an API performed by an AI service. OpenAI examples include input, cached input. Anthropic examples include: input, web_search. |
| Provider | The name of the AI tool providing the data, for example, OpenAI or Anthropic |
GenAI labels
Below are the GenAI system labels that you can use in the DoiT platform. The GenAI system labels are grouped in the GenAI section.
| Label | Description |
|---|---|
| API Key ID | The unique identifier of the AI key. |
| API Key Name | The name of the AI API key. |
| Base Model | The identifier of an AI model offering. For example, gpt-4.1. |
| Cached | Indicates that the input cost has been optimized or reused. This is either true or false. |
| Media Format | For models that support multiple media types, the media format distinguishes whether the service was processing audio or text. For example, audio. |
| Model | The identifier of an AI model offering. For example, gpt-4o-audio-preview. |
| Model Version | The version of an AI model offering. For example, 2024-12-17. |
| Organization Name | The unique identifier for the AI organization. |
| User Name | The name of a specific user in your AI organization. |
| User ID | The unique identifier of a specific user in your AI organization. |
| Model Family | A group of related AI models that share a common architecture and training methodology. OpenAI examples include: GPT, Codex. Anthropic examples include: Claude. |
| Token Type | The fundamental unit of data that the model processes and uses for its input and output. |
Example report
The GenAI Lens dashboard contains several preset report widgets to help you jump start the GenAI spend and usage analysis. You can adjust the configurations of a preset report or create your own from scratch to dive deeper into GenAI data.
The example below shows the usage costs in the last month for Completions API by organization.
