> ## Documentation Index > Fetch the complete documentation index at: https://docs.axilio.ai/llms.txt > Use this file to discover all available pages before exploring further. # List a run's steps > Lists a run's model steps from its transcript, oldest first: the messages each step sent, the model's answer, links to its screenshots and its cost. Empty once the transcript has passed its retention, or when your organization keeps none. Minimum role required: Viewer ## OpenAPI ````yaml /api-reference/openapi-backend.json get /runs/{run_id}/steps openapi: 3.1.0 info: description: Axilio backend HTTP API. title: Axilio API version: 0.155.0 servers: - url: https://api.axilio.ai/api/v1 description: Production security: [] tags: - name: Agents - name: API Keys - name: Billing - name: Conversations - name: Files - name: Messages - name: Models - name: Organization - name: Phones - name: Runs - name: Sessions - name: Skill - name: Usage - name: Webhooks paths: /runs/{run_id}/steps: get: tags: - Runs summary: List a run's steps description: >- Lists a run's model steps from its transcript, oldest first: the messages each step sent, the model's answer, links to its screenshots and its cost. Empty once the transcript has passed its retention, or when your organization keeps none. operationId: runs_list_steps parameters: - description: The run's id. in: path name: run_id required: true schema: description: The run's id. format: uuid type: string - description: The next_cursor of the page before; leave out for the first page. explode: false in: query name: cursor schema: description: The next_cursor of the page before; leave out for the first page. type: string - description: Page size. explode: false in: query name: limit schema: default: 20 description: Page size. format: int64 maximum: 100 minimum: 1 type: integer responses: '200': content: application/json: schema: $ref: '#/components/schemas/AgentRunStepList' description: OK '400': content: application/problem+json: schema: $ref: '#/components/schemas/V2ErrorModel' description: Bad Request '403': content: application/problem+json: schema: $ref: '#/components/schemas/V2ErrorModel' description: Forbidden '404': content: application/problem+json: schema: $ref: '#/components/schemas/V2ErrorModel' description: Not Found '422': content: application/problem+json: schema: $ref: '#/components/schemas/V2ErrorModel' description: Unprocessable Entity '500': content: application/problem+json: schema: $ref: '#/components/schemas/V2ErrorModel' description: Internal Server Error security: - apiKeyAuth: [] components: schemas: AgentRunStepList: additionalProperties: false description: >- One page of an agent run's steps, oldest first. Empty once the run's transcript has passed its retention, or when the organization keeps none. properties: next_cursor: description: Pass as cursor for the next page; absent on the last page. type: string steps: description: The steps on this page. items: $ref: '#/components/schemas/AgentRunStep' type: - array - 'null' required: - steps type: object V2ErrorModel: additionalProperties: false description: >- Error response, following RFC 9457 (Problem Details for HTTP APIs). Returned with a application/problem+json content type. properties: detail: description: >- A human-readable explanation specific to this occurrence of the problem. examples: - Property foo is required but is missing. type: string errors: description: Optional list of individual error details items: $ref: '#/components/schemas/V2ErrorDetail' type: - array - 'null' instance: description: >- A URI reference that identifies the specific occurrence of the problem. examples: - https://example.com/error-log/abc123 format: uri type: string status: description: HTTP status code examples: - 400 format: int64 type: integer title: description: >- A short, human-readable summary of the problem type. This value should not change between occurrences of the error. examples: - Bad Request type: string type: default: about:blank description: A URI reference to human-readable documentation for the error. examples: - https://example.com/errors/example format: uri type: string type: object AgentRunStep: additionalProperties: false description: >- One model step of an agent run: what the step sent the model, its answer and what it cost. properties: compaction: $ref: '#/components/schemas/AgentRunStepCompaction' description: >- Set when the run's conversation was compacted before this step: its earlier steps were dropped from what the model was sent, leaving a note of what they did. ended_at: description: When the step ended. format: date-time type: string error: description: Why the step failed, if it did. type: string finish_reason: description: Why the model stopped. type: string images: description: >- Short-lived links to the step's screenshots, in the order messages refer to them. items: type: string type: - array - 'null' messages: description: >- The messages the step added to the conversation, as the model received them. A message part refers to a screenshot by its index in images. A message a person sent the run while it worked is a user message with source "person" and message, the text as they sent it. items: {} type: - array - 'null' model: description: The model that answered the step. type: string response: description: 'The model''s answer: its text and the tool calls it made.' started_at: description: When the step started. format: date-time type: string step: description: The step's number in the run, from 1. format: int64 type: integer usage: $ref: '#/components/schemas/AgentRunStepUsage' description: The step's tokens and cost. required: - step - model - started_at - ended_at - messages type: object V2ErrorDetail: additionalProperties: false description: >- One specific problem within an error response, locating the offending part of the request. properties: location: description: >- Where the error occurred, e.g. 'body.items[3].tags' or 'path.thing-id' type: string message: description: Error message text type: string value: description: The value at the given location type: object AgentRunStepCompaction: additionalProperties: false properties: dropped_steps: description: >- How many of the run's earlier steps were dropped from the conversation. format: int64 type: integer note: description: >- What the model read in their place: what each dropped step did, and what people said in them. type: string required: - dropped_steps - note type: object AgentRunStepUsage: additionalProperties: false description: A model step's tokens and cost. properties: cache_read_tokens: description: >- Of the tokens sent, those read from the model provider's prompt cache, at the model's cache-read rate. format: int64 type: integer cache_write_tokens: description: >- Of the tokens sent, those written to the model provider's prompt cache, at the model's cache-write rate. format: int64 type: integer completion_tokens: description: Tokens the model answered with. format: int64 type: integer cost_microdollars: description: What the step cost, in microdollars. format: int64 type: integer prompt_tokens: description: Tokens the step sent, the cached ones included. format: int64 type: integer required: - prompt_tokens - cache_read_tokens - cache_write_tokens - completion_tokens - cost_microdollars type: object securitySchemes: apiKeyAuth: description: Customer API key (axl_ prefix). in: header name: X-Axilio-Api-Key type: apiKey ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.