> ## Documentation Index > Fetch the complete documentation index at: https://docs.textql.com/llms.txt > Use this file to discover all available pages before exploring further. # Get Llm Usage ## OpenAPI ````yaml api-reference/speakeasy/textql-api-with-code-samples.yaml POST /textql.rpc.public.chat.ChatService/GetLlmUsage openapi: 3.1.0 info: title: TextQL API version: 1.0.0 description: | TextQL public API. Generated from protobuf service definitions; internal endpoints are excluded via google.api.visibility / file_visibility. servers: - url: https://app.textql.com security: - apiKey: [] tags: - name: DashboardService - name: AppService description: |- AppService manages data apps: the generative app execution primitive. An app is agent-authored single-file HTML/JS/CSS executing in a CSP sandbox, fed a snapshot of its declared data sources. First-class resource, not a dashboard. - name: ConnectorService - name: PowerBIService - name: TableauService - name: DatasetService - name: OntologyManagementService - name: ChatService - name: AgentService - name: AuditLogService - name: MCPService - name: MetricsExportService - name: ObservabilityService - name: PlaybookService - name: RBACService description: RBAC service for managing roles, permissions, and access control - name: SandboxAdminService - name: SandboxQueryService - name: SandboxCapabilityService - name: ScimService - name: SecretService - name: SlackService - name: TeamsService paths: /textql.rpc.public.chat.ChatService/GetLlmUsage: post: tags: - ChatService summary: GetLlmUsage operationId: ChatService_GetLlmUsage parameters: - name: Connect-Protocol-Version in: header required: true schema: $ref: '#/components/schemas/connect-protocol-version' - name: Connect-Timeout-Ms in: header schema: $ref: '#/components/schemas/connect-timeout-header' requestBody: content: application/json: schema: $ref: '#/components/schemas/textql.rpc.public.chat.GetLlmUsageRequest' required: true responses: '200': description: Success content: application/json: schema: $ref: >- #/components/schemas/textql.rpc.public.chat.GetLlmUsageResponse default: description: Error content: application/json: schema: $ref: '#/components/schemas/connect.error' x-codeSamples: - lang: typescript label: TypeScript (SDK) source: |- import { Textql } from "@textql/sdk"; const textql = new Textql({ apiKey: process.env["TEXTQL_API_KEY"] ?? "", }); async function run() { const result = await textql.chats.getLlmUsage({ body: {}, }); console.log(result); } run(); - lang: python label: Python (SDK) source: |- import os from textql_sdk import Textql with Textql( api_key=os.getenv("TEXTQL_API_KEY", ""), ) as textql: res = textql.chats.get_llm_usage() # Handle response print(res) components: schemas: connect-protocol-version: type: number title: Connect-Protocol-Version enum: - 1 description: Define the version of the Connect protocol const: 1 default: 1 connect-timeout-header: type: number title: Connect-Timeout-Ms description: Define the timeout, in ms textql.rpc.public.chat.GetLlmUsageRequest: type: object properties: chatId: type: string title: chat_id includeCosts: type: boolean title: include_costs title: GetLlmUsageRequest additionalProperties: false textql.rpc.public.chat.GetLlmUsageResponse: type: object properties: usage: type: array items: $ref: '#/components/schemas/textql.rpc.public.chat.LlmUsage' title: usage contextWindowUsed: type: number title: context_window_used format: double description: 'range: [0, 1]' estimatedCost: type: number title: estimated_cost format: double description: Estimated LLM-token cost (USD, list model prices). LLM only. nullable: true estimatedComputeCost: type: number title: estimated_compute_cost format: double description: >- Estimated sandbox/compute cost for this chat (USD): chat sandbox-seconds → ACUs → USD at the org's effective rate. Add to estimated_cost for the thread's total cost. Requires the console rate (0/omitted if unavailable). nullable: true sandboxId: type: string title: sandbox_id description: >- The chat's sandbox id ({orgID}-{chatID}), set when the thread used any sandbox compute. Lets the UI deep-link to the sandbox detail. Empty/omitted when the thread had no sandbox usage. nullable: true estimatedComputeAcus: type: number title: estimated_compute_acus format: double description: >- Sandbox compute usage for this chat in ACUs (sandbox-seconds / 3600 × ACUs per instance-hour). The metered unit behind estimated_compute_cost; shown alongside the dollars. Independent of the console $ rate, so present whenever the thread used a sandbox. nullable: true title: GetLlmUsageResponse additionalProperties: false connect.error: type: object properties: code: type: string examples: - not_found enum: - canceled - unknown - invalid_argument - deadline_exceeded - not_found - already_exists - permission_denied - resource_exhausted - failed_precondition - aborted - out_of_range - unimplemented - internal - unavailable - data_loss - unauthenticated description: >- The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. message: type: string description: >- A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. details: type: array items: $ref: '#/components/schemas/connect.error_details.Any' description: >- A list of messages that carry the error details. There is no limit on the number of messages. title: Connect Error additionalProperties: true description: >- Error type returned by Connect: https://connectrpc.com/docs/go/errors/#http-representation textql.rpc.public.chat.LlmUsage: type: object properties: inputTokens: type: - integer - string title: input_tokens format: int64 cacheCreationInputTokens: type: - integer - string title: cache_creation_input_tokens format: int64 cacheReadInputTokens: type: - integer - string title: cache_read_input_tokens format: int64 outputTokens: type: - integer - string title: output_tokens format: int64 modelName: type: string title: model_name timestamp: $ref: '#/components/schemas/google.protobuf.Timestamp' title: timestamp title: LlmUsage additionalProperties: false connect.error_details.Any: type: object properties: type: type: string description: >- A URL that acts as a globally unique identifier for the type of the serialized message. For example: `type.googleapis.com/google.rpc.ErrorInfo`. This is used to determine the schema of the data in the `value` field and is the discriminator for the `debug` field. value: type: string format: binary description: >- The Protobuf message, serialized as bytes and base64-encoded. The specific message type is identified by the `type` field. debug: oneOf: - type: object title: Any additionalProperties: true description: Detailed error information. discriminator: propertyName: type title: Debug description: >- Deserialized error detail payload. The 'type' field indicates the schema. This field is for easier debugging and should not be relied upon for application logic. additionalProperties: true description: >- Contains an arbitrary serialized message along with a @type that describes the type of the serialized message, with an additional debug field for ConnectRPC error details. google.protobuf.Timestamp: type: string examples: - '2023-01-15T01:30:15.01Z' - '2024-12-25T12:00:00Z' format: date-time description: >- A Timestamp represents a point in time independent of any time zone or local calendar, encoded as a count of seconds and fractions of seconds at nanosecond resolution. The count is relative to an epoch at UTC midnight on January 1, 1970, in the proleptic Gregorian calendar which extends the Gregorian calendar backwards to year one. All minutes are 60 seconds long. Leap seconds are "smeared" so that no leap second table is needed for interpretation, using a [24-hour linear smear](https://developers.google.com/time/smear). The range is from 0001-01-01T00:00:00Z to 9999-12-31T23:59:59.999999999Z. By restricting to that range, we ensure that we can convert to and from [RFC 3339](https://www.ietf.org/rfc/rfc3339.txt) date strings. # Examples Example 1: Compute Timestamp from POSIX `time()`. Timestamp timestamp; timestamp.set_seconds(time(NULL)); timestamp.set_nanos(0); Example 2: Compute Timestamp from POSIX `gettimeofday()`. struct timeval tv; gettimeofday(&tv, NULL); Timestamp timestamp; timestamp.set_seconds(tv.tv_sec); timestamp.set_nanos(tv.tv_usec * 1000); Example 3: Compute Timestamp from Win32 `GetSystemTimeAsFileTime()`. FILETIME ft; GetSystemTimeAsFileTime(&ft); UINT64 ticks = (((UINT64)ft.dwHighDateTime) << 32) | ft.dwLowDateTime; // A Windows tick is 100 nanoseconds. Windows epoch 1601-01-01T00:00:00Z // is 11644473600 seconds before Unix epoch 1970-01-01T00:00:00Z. Timestamp timestamp; timestamp.set_seconds((INT64) ((ticks / 10000000) - 11644473600LL)); timestamp.set_nanos((INT32) ((ticks % 10000000) * 100)); Example 4: Compute Timestamp from Java `System.currentTimeMillis()`. long millis = System.currentTimeMillis(); Timestamp timestamp = Timestamp.newBuilder().setSeconds(millis / 1000) .setNanos((int) ((millis % 1000) * 1000000)).build(); Example 5: Compute Timestamp from Java `Instant.now()`. Instant now = Instant.now(); Timestamp timestamp = Timestamp.newBuilder().setSeconds(now.getEpochSecond()) .setNanos(now.getNano()).build(); Example 6: Compute Timestamp from current time in Python. timestamp = Timestamp() timestamp.GetCurrentTime() # JSON Mapping In JSON format, the Timestamp type is encoded as a string in the [RFC 3339](https://www.ietf.org/rfc/rfc3339.txt) format. That is, the format is "{year}-{month}-{day}T{hour}:{min}:{sec}[.{frac_sec}]Z" where {year} is always expressed using four digits while {month}, {day}, {hour}, {min}, and {sec} are zero-padded to two digits each. The fractional seconds, which can go up to 9 digits (i.e. up to 1 nanosecond resolution), are optional. The "Z" suffix indicates the timezone ("UTC"); the timezone is required. A proto3 JSON serializer should always use UTC (as indicated by "Z") when printing the Timestamp type and a proto3 JSON parser should be able to accept both UTC and other timezones (as indicated by an offset). For example, "2017-01-15T01:30:15.01Z" encodes 15.01 seconds past 01:30 UTC on January 15, 2017. In JavaScript, one can convert a Date object to this format using the standard [toISOString()](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Date/toISOString) method. In Python, a standard `datetime.datetime` object can be converted to this format using [`strftime`](https://docs.python.org/2/library/time.html#time.strftime) with the time format spec '%Y-%m-%dT%H:%M:%S.%fZ'. Likewise, in Java, one can use the Joda Time's [`ISODateTimeFormat.dateTime()`]( http://joda-time.sourceforge.net/apidocs/org/joda/time/format/ISODateTimeFormat.html#dateTime() ) to obtain a formatter capable of generating timestamps in this format. securitySchemes: apiKey: type: apiKey in: header name: tql_api_key ````