> ## Documentation Index > Fetch the complete documentation index at: https://sidenet.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # List requests > The request log, newest first: one row per chat turn, workflow run or experiment item, with who asked, what ran, what it cost, how long it took, the user's vote and any scores. Filters are ANDed. Scorer runs are left out unless `kind=score`; each row reports them under `scoring`. The window defaults to the last 30 days; `limit` goes up to 1000 for exports. ## OpenAPI ````yaml /api-reference/openapi.json get /v1/requests openapi: 3.1.0 info: title: Sidenet API version: 1.0.0 description: >- Sidenet HTTP endpoints exposed by the Sidenet Studio. All routes require an api key that can be generated through the studio in studio.sidenet.ai. servers: - url: https://api.sidenet.ai security: - bearerAuth: [] paths: /v1/requests: get: tags: - Observability summary: List requests description: >- The request log, newest first: one row per chat turn, workflow run or experiment item, with who asked, what ran, what it cost, how long it took, the user's vote and any scores. Filters are ANDed. Scorer runs are left out unless `kind=score`; each row reports them under `scoring`. The window defaults to the last 30 days; `limit` goes up to 1000 for exports. parameters: - name: from in: query required: false schema: type: string format: date-time example: '2026-10-01T00:00:00Z' description: 'Start of the window (inclusive). Default: 30 days before `to`.' - name: to in: query required: false schema: type: string format: date-time example: '2026-11-01T00:00:00Z' description: 'End of the window (exclusive). Default: now.' - name: kind in: query required: false schema: type: string enum: - chat - workflow - experiment - score description: Only this kind of request. - name: status in: query required: false schema: type: string enum: - success - error description: Only requests that failed, or only those that did not. - name: environment in: query required: false schema: type: string example: prod,staging description: Comma-separated environments. - name: group_id in: query required: false schema: type: string example: grp_84f20c19 description: Comma-separated billing group ids (your stable ids). - name: agent_id in: query required: false schema: type: string example: 6f1c0f4e-2b7a-4a51-9a2f-0c9d1b3e5a10 description: Comma-separated agent ids; every version of the agent matches. - name: agent_version_id in: query required: false schema: type: string example: b3f7a2c8-5d19-4e6b-8f02-1a4c9e7d3b55 description: One agent version. - name: workflow_id in: query required: false schema: type: string example: 4c2f9e18-7a63-4d05-b1e8-93a7c0f2d641 description: Comma-separated workflow ids; every version matches. - name: workflow_version_id in: query required: false schema: type: string example: e81b4a72-0c95-4f38-a6d2-5b17e9c4038f description: One workflow version. - name: copilot_id in: query required: false schema: type: string example: cccccccc-0000-4000-8000-000000000001 description: Comma-separated copilot ids. - name: experiment_id in: query required: false schema: type: string example: exp_7f31a9c2 description: The items of one experiment. - name: model in: query required: false schema: type: string example: openai/gpt-4o description: Comma-separated served models. - name: source in: query required: false schema: type: string example: SDK-v2 description: Comma-separated sources. - name: user_id in: query required: false schema: type: string example: user_4821 description: Comma-separated end user ids (your ids for them). - name: thread_id in: query required: false schema: type: string example: thread_2f81c04a description: One conversation. - name: search in: query required: false schema: type: string example: 8f2c1d4e6a7b4c9d description: >- A request id, message id or trace id, or a prefix of a request or message id. - name: order in: query required: false schema: type: string enum: - desc - asc default: desc description: By start time. - name: page in: query required: false schema: type: integer minimum: 0 default: 0 description: 0-based page. - name: limit in: query required: false schema: type: integer default: 50 maximum: 1000 responses: '200': description: The requests content: application/json: schema: type: object properties: requests: type: array items: type: object properties: id: type: string description: >- The request id: one per inbound request or run, shared by everything it did. kind: type: string enum: - chat - workflow - experiment - score description: >- What ran: a chat turn, a workflow run, an experiment item, or a scorer run. status: type: string enum: - success - error error: type: object nullable: true description: >- The error that ended the turn or run, when it failed. started_at: type: string format: date-time ended_at: type: string format: date-time nullable: true latency_ms: type: integer nullable: true description: Start to end of the turn or run. environment: type: string nullable: true description: >- `dev`, `staging` or `prod` for chat; `production` or `preview` for workflow runs; `experiment` for experiment items. source: type: string nullable: true description: >- What the client declared (`X-Source`), or the run trigger for workflows. group: type: object properties: id: type: string nullable: true description: >- Your id for the billing group (null for groups created before stable ids existed). name: type: string nullable: true nullable: true description: The billing group the request was attributed to. user_id: type: string nullable: true description: >- The end user the request ran for (your id for them, as sent on the session mint or `X-User-Id`). thread_id: type: string nullable: true message_id: type: string nullable: true description: The assistant message this turn produced. prompt: type: object properties: message_id: type: string description: The user message that started the turn. text: type: string description: >- Its text. The list clips it to 1 000 characters; `GET /v1/requests/{id}` returns it whole. truncated: type: boolean description: True when `text` was clipped. nullable: true description: >- What the user asked: the user message saved just before the assistant message in its thread. Null for runs, experiment items and turns whose user message is not in the thread. trace_ids: type: array items: type: string description: >- The traces the request produced (a routed chat turn has two: the classifier and the answer). agent: type: object properties: id: type: string name: type: string nullable: true version_id: type: string version: type: integer nullable: true nullable: true description: The agent version that answered, when one did. workflow: type: object properties: id: type: string name: type: string nullable: true version_id: type: string version: type: integer nullable: true nullable: true description: The workflow version that ran, when one did. copilot: type: object properties: id: type: string environment: type: string nullable: true network: type: object properties: id: type: string name: type: string nullable: true nullable: true nullable: true description: >- The copilot the request came through, for routed chat. experiment_id: type: string nullable: true target: type: string nullable: true description: >- For built-in targets without a version: `Clarification`, `Dashboard`, `Score: `. model: type: string nullable: true description: >- The model that actually served the main answer (after any routing policy). model_profile: type: string nullable: true description: >- The model profile the copilot's model classifier chose for the turn (`default` included), which is what put the turn on `model` when it differs from the agent's own. Null when no classifier ran. cost: type: number nullable: true description: >- USD spend of the request, every participant included. usage: type: object properties: input_tokens: type: number nullable: true output_tokens: type: number nullable: true total_tokens: type: number nullable: true nullable: true cost_breakdown: type: object description: >- Per participant (`main`, `handoff-agent`, `followup-agent`, `step:`…): `{ cost, usage, model }`. additionalProperties: true participants: type: array nullable: true items: type: object additionalProperties: true description: >- The agents and tools that ran, each with a success flag. feedback: type: object properties: rating: type: number nullable: true comment: type: string nullable: true nullable: true description: The user's vote on the answer, when they gave one. scores: type: array items: type: object properties: id: type: string scorer_id: type: string name: type: string nullable: true score: type: number description: The scores recorded on the request's traces. scoring: type: object properties: runs: type: integer cost: type: number description: >- The scorer runs that scored this request and what they cost. pagination: type: object properties: total: type: integer page: type: integer limit: type: integer hasMore: type: boolean example: requests: - id: 8f2c1d4e6a7b4c9d kind: chat status: success error: null started_at: '2026-10-27T10:00:00.000Z' ended_at: '2026-10-27T10:00:04.210Z' latency_ms: 4210 environment: prod source: SDK-v2 group: id: grp_84f20c19 name: Acme user_id: user_4821 thread_id: thread_2f81c04a message_id: msg_9c41b0e7 prompt: message_id: 3b9e1c7a-5d2f-4e8b-9a6c-1f0d2e3a4b5c text: Where is my order 4821? truncated: false trace_ids: - 0af7651916cd43dd8448eb211c80319c - 5c1e9a2b7d3f4e6a8b9c0d1e2f3a4b5c agent: id: 6f1c0f4e-2b7a-4a51-9a2f-0c9d1b3e5a10 name: Support version_id: b3f7a2c8-5d19-4e6b-8f02-1a4c9e7d3b55 version: 4 workflow: null copilot: id: cccccccc-0000-4000-8000-000000000001 environment: prod network: id: '12' name: Acme network experiment_id: null target: null model: openai/gpt-4o model_profile: default cost: 0.0123 usage: input_tokens: 1210 output_tokens: 188 total_tokens: 1398 cost_breakdown: main: cost: 0.0118 usage: inputTokens: 1180 outputTokens: 184 model: openai/gpt-4o handoff-agent: cost: 0.0005 usage: inputTokens: 30 outputTokens: 4 model: openai/gpt-4o-mini participants: - type: agent id: support-agent name: Support - type: tool id: Acme_CRM_get_customer name: Acme_CRM_get_customer success: true feedback: rating: 1 comment: null scores: - id: f2c1a7e4-6b3d-4a95-8e10-c7d2b9f4a301 scorer_id: answer-relevancy name: Answer Relevancy score: 0.85 scoring: runs: 1 cost: 0.0021 pagination: total: 1 page: 0 limit: 50 hasMore: false '400': description: Bad window or filter content: application/json: schema: type: object properties: error: type: string description: The class of failure. details: type: string description: What specifically went wrong. example: error: Bad request details: kind must be one of chat, workflow, experiment, score components: securitySchemes: bearerAuth: type: http scheme: bearer description: >- Organization API key, generated in studio.sidenet.ai. Backend only — never in a browser. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.