> ## Documentation Index > Fetch the complete documentation index at: https://developers.telnyx.com/llms.txt > Use this file to discover all available pages before exploring further. # List spend logs > Lists the requests the instance served with its keys, newest first, one page at a time. The window defaults to the last 24 hours and spans at most 31 days. A row appears a few seconds after its request. The instance must be `ready`; otherwise the request answers `409`. ## OpenAPI ````yaml /openapi/source/external/agent-gateway/agent-gateway.json get /agent_gateways/{instance_id}/spend_logs openapi: 3.1.0 info: version: 1.0.0 title: Telnyx API x-latency-category: interactive x-endpoint-cost: light description: >- Agent Gateway authenticates, authorizes, and audits the requests agents send to models, tools, and other agents. Each gateway runs as a dedicated instance on the account's [*Network*](https://developers.telnyx.com/docs/network/overview). This API creates, lists, and deletes instances, and manages the keys, teams, spend logs, MCP servers, APIs, tool permissions, and guardrails on them. Each instance serves an OpenAI-compatible API at its `gateway_url`. servers: - url: https://api.telnyx.com/v2 description: Telnyx API v2 security: - bearerAuth: [] tags: - name: Agent Gateways description: Create, list, retrieve, and delete Agent Gateway instances. - name: Agent Gateway Keys description: Keys on an instance. - name: Agent Gateway Teams description: 'Teams on an instance: shared model lists, budgets, and rate limits.' - name: Agent Gateway Spend Logs description: The requests an instance served, with their cost. - name: Agent Gateway MCP Servers description: MCP servers on an instance, served to agents at one MCP endpoint. - name: Agent Gateway APIs description: REST APIs on an instance, served to agents as tools. - name: Agent Gateway Tool Permissions description: The MCP servers and tools a key or team may use. - name: Agent Gateway Guardrails description: Checks an instance runs on model and tool requests. - name: Agent Gateway Policies description: Named sets of guardrails an instance applies to requests. - name: Agent Gateway Policy Attachments description: Where an instance applies each policy. paths: /agent_gateways/{instance_id}/spend_logs: get: tags: - Agent Gateway Spend Logs summary: List spend logs description: >- Lists the requests the instance served with its keys, newest first, one page at a time. The window defaults to the last 24 hours and spans at most 31 days. A row appears a few seconds after its request. The instance must be `ready`; otherwise the request answers `409`. operationId: ListAgentGatewaySpendLogs parameters: - name: instance_id in: path required: true description: The Agent Gateway's `id`. schema: type: string format: uuid example: ecffdf4b-93ea-4a7b-8295-51dfd2077996 - name: page[number] in: query required: false description: The page to return, counting from 1. schema: type: integer minimum: 1 default: 1 - name: page[size] in: query required: false description: Results per page. schema: type: integer minimum: 1 maximum: 100 default: 50 - name: start in: query required: false description: >- The window's start, an RFC 3339 timestamp with an offset. Defaults to 24 hours before `end`. schema: type: string format: date-time example: '2026-10-21T00:00:00Z' - name: end in: query required: false description: >- The window's end, an RFC 3339 timestamp with an offset. Defaults to now. schema: type: string format: date-time example: '2026-10-22T00:00:00Z' - name: key_id in: query required: false description: Only the requests made with this key. schema: type: string pattern: ^[0-9a-f]{64}$ - name: team_id in: query required: false description: Only the requests made with this team's keys. schema: type: string format: uuid responses: '200': description: One page of spend logs content: application/json: schema: $ref: '#/components/schemas/AgentGatewaySpendLogListResponse' example: data: - id: chatcmpl-1c0032cc-3d9f-439f-af62-b7f2b6623da4 key_id: >- 5f1c3a0e9b7d4c2a8e6f0b1d3c5a7e9f2b4d6c8a0e1f3a5c7e9b1d3f5a7c9e0b team_id: 0b6c5d4e-3f2a-4b1c-9d8e-7f6a5b4c3d2e model: zai-org/GLM-5.3-Flash operation: acompletion status: success spend: 0.00027747 prompt_tokens: 22 completion_tokens: 610 total_tokens: 632 started_at: '2026-10-21T19:41:02.114000Z' ended_at: '2026-10-21T19:41:04.879000Z' duration_ms: 2765 meta: total_results: 1 page_number: 1 page_size: 50 total_pages: 1 total_results_capped: false '400': description: The window is longer than 31 days content: application/json: schema: $ref: '#/components/schemas/TelnyxErrors' example: errors: - code: '10033' title: Value outside of range detail: >- The value is outside of allowed range the start to 31 days after it source: parameter: end meta: url: https://developers.telnyx.com/docs/overview/errors/10033 '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/TelnyxErrors' example: errors: - code: '10009' title: Authentication failed detail: >- The required authentication headers were either invalid or not included in the request. meta: url: https://developers.telnyx.com/docs/overview/errors/10009 '404': description: Not found content: application/json: schema: $ref: '#/components/schemas/TelnyxErrors' example: errors: - code: '10005' title: Resource not found detail: The requested resource or URL could not be found. meta: url: https://developers.telnyx.com/docs/overview/errors/10005 '409': description: The instance is not `ready` content: application/json: schema: $ref: '#/components/schemas/TelnyxErrors' example: errors: - code: '99901' title: Instance not ready detail: The instance is not ready; its engine is not running. '502': description: The instance's engine did not answer content: application/json: schema: $ref: '#/components/schemas/TelnyxErrors' example: errors: - code: '99903' title: Engine unavailable detail: The instance's engine did not answer; try again shortly. components: schemas: AgentGatewaySpendLogListResponse: type: object required: - data - meta properties: data: type: array items: $ref: '#/components/schemas/AgentGatewaySpendLog' meta: $ref: '#/components/schemas/AgentGatewaySpendLogPageMeta' TelnyxErrors: type: object properties: errors: type: array items: $ref: '#/components/schemas/TelnyxError' AgentGatewaySpendLog: type: object description: One request the instance served. required: - id - key_id - team_id - model - operation - status - spend - prompt_tokens - completion_tokens - total_tokens - started_at - ended_at - duration_ms properties: id: type: string description: The request's ID. key_id: anyOf: - type: string - type: 'null' description: The key the request used. team_id: anyOf: - type: string - type: 'null' description: The key's team. model: anyOf: - type: string - type: 'null' description: >- The Telnyx Inference model that answered, such as `zai-org/GLM-5.3-Flash`. For an MCP tool request, `MCP: ` and the tool's name. operation: type: string description: >- The request type. `acompletion` is a chat completion, `aresponses` a response, `anthropic_messages` a message, `call_mcp_tool` an MCP tool request, and `list_mcp_tools` an MCP tool list. status: anyOf: - type: string - type: 'null' description: '`success` or `failure`.' spend: type: number description: >- What the request cost, in USD, with its tokens at Telnyx Inference prices. prompt_tokens: type: integer description: Input tokens. completion_tokens: type: integer description: Output tokens, reasoning included. total_tokens: type: integer description: Input and output tokens. started_at: type: string format: date-time description: When the request started. ended_at: anyOf: - type: string format: date-time - type: 'null' description: When the request ended. duration_ms: anyOf: - type: integer - type: 'null' description: How long the request took, in milliseconds. AgentGatewaySpendLogPageMeta: type: object required: - total_results - page_number - page_size - total_pages - total_results_capped properties: total_results: type: integer description: Results across every page. page_number: type: integer description: The page returned, counting from 1. page_size: type: integer description: Results per page. total_pages: type: integer description: Pages that can be requested; 0 when nothing matched. total_results_capped: type: boolean description: >- `true` when the window holds more than 10,000 rows. The two totals are then lower bounds: narrow the window, or page until a page comes back empty. TelnyxError: type: object properties: code: type: string title: type: string detail: type: string source: type: object properties: pointer: type: string parameter: type: string meta: type: object properties: url: type: string securitySchemes: bearerAuth: type: http scheme: bearer description: Telnyx API key ````