|
<< Click to Display Table of Contents >> Raynet One Data Hub > 2026.2 > Connectors > Alphabetic Connector List > OpenAI > Extracted Data Tables |
The OpenAI connector produces the following output tables. Each table corresponds to a specific OpenAI API endpoint and contains the data collected by the associated query type.
Contains usage data for audio speech generation requests made by the organization. Each row represents an aggregated usage record for a specific time bucket, model, project, user, or API key combination.
Column |
Type |
Description |
|---|---|---|
apiKeyId |
String |
The ID of the API key used for the request. |
characters |
Integer |
The number of characters processed in audio speech generation requests. |
model |
String |
The name of the model used for the request. |
numModelRequests |
Integer |
The number of API requests made to the model within the time bucket. |
object |
String |
The object type identifier returned by the API. |
projectId |
String |
The ID of the OpenAI project associated with the usage record. |
userId |
String |
The ID of the user who made the request. |
Contains usage data for audio transcription requests. Each row represents an aggregated usage record showing the number of seconds transcribed per model, project, user, or API key combination.
Column |
Type |
Description |
|---|---|---|
apiKeyId |
String |
The ID of the API key used for the request. |
model |
String |
The name of the model used for transcription. |
numModelRequests |
Integer |
The number of API requests made to the model within the time bucket. |
object |
String |
The object type identifier returned by the API. |
projectId |
String |
The ID of the OpenAI project associated with the usage record. |
seconds |
Integer |
The total number of seconds of audio transcribed within the time bucket. |
userId |
String |
The ID of the user who made the request. |
Contains usage data for Code Interpreter sessions. Each row represents the number of Code Interpreter sessions used within a time bucket for a specific project.
Column |
Type |
Description |
|---|---|---|
numSessions |
Integer |
The number of Code Interpreter sessions used within the time bucket. |
object |
String |
The object type identifier returned by the API. |
projectId |
String |
The ID of the OpenAI project associated with the usage record. |
Contains usage data for chat completion and text generation requests. Each row shows token consumption broken down by input tokens, output tokens, cached tokens, and audio tokens per model, project, user, or API key combination. This table is useful for tracking how many tokens were consumed per project or per user.
Column |
Type |
Description |
|---|---|---|
object |
String |
The object type identifier returned by the API. |
inputTokens |
Integer |
The total number of input tokens consumed within the time bucket. |
outputTokens |
Integer |
The total number of output tokens generated within the time bucket. |
inputCachedTokens |
Integer |
The number of input tokens served from cache, which reduces cost. |
inputAudioTokens |
Integer |
The number of audio input tokens consumed within the time bucket. |
outputAudioTokens |
Integer |
The number of audio output tokens generated within the time bucket. |
numModelRequests |
Integer |
The number of API requests made to the model within the time bucket. |
projectId |
String |
The ID of the OpenAI project associated with the usage record. |
userId |
String |
The ID of the user who made the request. |
apiKeyId |
String |
The ID of the API key used for the request. |
model |
String |
The name of the model used (for example, gpt-4 or gpt-4-turbo). |
batch |
Boolean |
Indicates whether the request was processed as a batch job. |
Contains cost breakdown data for the organization. Each row represents the monetary cost incurred within a time bucket, grouped by project and line item. Use this table to track how much money was spent per project or per service type.
Column |
Type |
Description |
|---|---|---|
currency |
String |
The currency in which the cost is denominated (for example, usd). |
value |
Decimal |
The cost amount for the time bucket, rounded to two decimal places. |
lineItem |
String |
The service or model that generated the cost (for example, gpt-4-completions). |
object |
String |
The object type identifier returned by the API. |
projectId |
String |
The ID of the OpenAI project associated with the cost record. |
Contains usage data for embedding generation requests. Each row shows the number of input tokens consumed per model, project, user, or API key combination within a time bucket.
Column |
Type |
Description |
|---|---|---|
apiKeyId |
String |
The ID of the API key used for the request. |
inputTokens |
Integer |
The total number of input tokens used to generate embeddings within the time bucket. |
model |
String |
The name of the embedding model used. |
numModelRequests |
Integer |
The number of API requests made to the model within the time bucket. |
object |
String |
The object type identifier returned by the API. |
projectId |
String |
The ID of the OpenAI project associated with the usage record. |
userId |
String |
The ID of the user who made the request. |
Contains usage data for image generation, editing, and variation requests. Each row shows the number of images generated per model, size, source operation, project, user, or API key combination within a time bucket.
Column |
Type |
Description |
|---|---|---|
apiKeyId |
String |
The ID of the API key used for the request. |
images |
Integer |
The number of images generated within the time bucket. |
model |
String |
The name of the image model used (for example, dall-e-3). |
numModelRequests |
Integer |
The number of API requests made to the model within the time bucket. |
object |
String |
The object type identifier returned by the API. |
projectId |
String |
The ID of the OpenAI project associated with the usage record. |
size |
String |
The dimensions of the generated image (for example, 1024x1024). |
source |
String |
The type of image operation (image.generation, image.edit, or image.variation). |
userId |
String |
The ID of the user who made the request. |
Contains usage data for content moderation requests. Each row shows the number of input tokens processed per model, project, user, or API key combination within a time bucket.
Column |
Type |
Description |
|---|---|---|
apiKeyId |
String |
The ID of the API key used for the request. |
inputTokens |
Integer |
The total number of input tokens submitted for content moderation within the time bucket. |
model |
String |
The name of the moderation model used. |
numModelRequests |
Integer |
The number of API requests made to the model within the time bucket. |
object |
String |
The object type identifier returned by the API. |
projectId |
String |
The ID of the OpenAI project associated with the usage record. |
userId |
String |
The ID of the user who made the request. |
Contains storage usage data for vector stores. Each row shows the number of bytes used per project within a time bucket.
Column |
Type |
Description |
|---|---|---|
object |
String |
The object type identifier returned by the API. |
projectId |
String |
The ID of the OpenAI project associated with the vector store usage. |
usageBytes |
Integer |
The total number of bytes stored in vector stores within the time bucket. |
Contains a list of all projects within the OpenAI organization. Use this table to map project IDs to human-readable project names when analyzing usage data from other tables.
Column |
Type |
Description |
|---|---|---|
archivedAt |
Integer |
The Unix timestamp at which the project was archived. Null if the project is still active. |
createdAt |
Integer |
The Unix timestamp at which the project was created. |
id |
String |
The unique identifier for the project. This ID is used as a foreign key in other tables. |
name |
String |
The display name of the project. |
status |
String |
The status of the project (active or archived). |
Contains a list of all users in the OpenAI organization. Use this table to map user IDs to names and email addresses when analyzing usage data from other tables.
Column |
Type |
Description |
|---|---|---|
addedAt |
Integer |
The Unix timestamp at which the user was added to the organization. |
id |
String |
The unique identifier for the user. This ID is used as a foreign key in usage tables. |
name |
String |
The display name of the user. |
role |
String |
The role of the user in the organization (for example, owner or member). |
String |
The email address of the user. |
Contains a list of all Admin API Keys for the organization. Key values are returned in redacted form. Use this table to audit which API keys exist and when they were last used.
Column |
Type |
Description |
|---|---|---|
createdAt |
Integer |
The Unix timestamp at which the Admin API Key was created. |
lastUsedAt |
Integer |
The Unix timestamp of the last time the key was used to make an API request. |
id |
String |
The unique identifier for the Admin API Key. |
name |
String |
The display name assigned to the Admin API Key. |
redactedValue |
String |
A redacted representation of the key value with most characters masked. |
ownerId |
String |
The ID of the owner of the key. Refers to the id column in the owners table. |
Contains information about the owners of Admin API Keys. This table is populated alongside the adminApiKeys table and provides additional context about who holds each key.
Column |
Type |
Description |
|---|---|---|
createdAt |
Integer |
The Unix timestamp at which the owner record was created. |
id |
String |
The unique identifier for the owner. Referenced by the ownerId column in the adminApiKeys table. |
name |
String |
The display name of the owner. |
type |
String |
The type of the owner entity (for example, user or service_account). |
role |
String |
The role of the owner within the organization. |