> ## Documentation Index > Fetch the complete documentation index at: https://docs.replicas.dev/llms.txt > Use this file to discover all available pages before exploring further. # Send Message > Sends a message to an existing replica. Supports targeting a specific chat, choosing a coding agent and model, attaching images, and enabling plan mode. ## OpenAPI ````yaml /openapi.json post /v1/replica/{id}/messages openapi: 3.1.0 info: title: Replica API version: 2.0.0 description: >- The Replica API allows you to programmatically manage cloud workspaces for AI agents. Use this API to manage environments (the org-scoped primitive workspaces are created from — including variables, files, skills, MCPs, warm hooks, start hooks, and warm pools), create and manage replicas, send messages, manage chats, stream events, read connected repositories and repository sets, and configure automations. servers: - url: https://api.replicas.dev description: Production API security: - apiKey: [] tags: - name: Environments description: >- Manage environments — the primitive that workspaces are created from. Variables, files, skills, MCPs, warm-hooks, and warm-pools are all scoped to an environment. Every organization has a singleton Global environment whose values apply to every workspace. Personal environments are scoped to the authenticated user and can be standalone or source-backed by a team environment. - name: Repository description: >- Read repositories and repository sets connected to your organization. Repositories are the underlying GitHub-connection layer; bind them to an environment to use them in workspaces. - name: Replica description: >- Manage replicas (workspaces) for AI agents. Workspace creation with `POST /v1/replica` accepts API keys and workspace engine-secret authentication. Other Replica operations also accept logged-in user JWTs from first-party clients. - name: Terminal description: Manage interactive terminal sessions in active workspaces - name: Preview description: Manage public preview URLs for workspace ports - name: Profile description: Read and update the authenticated user's profile - name: Credentials description: >- Manage coding-agent credentials for an organization or the authenticated user - name: Preferences description: Manage organization behavior preferences - name: Slack description: Connect Slack identities and route threads to Replicas workspaces - name: Linear description: Connect Linear identities to Replicas accounts - name: Automation description: >- Create and manage automations that trigger replicas on a schedule or in response to events - name: Downloads description: Download Replicas applications - name: Media description: >- Read workspace media and obtain short-lived download or inline preview URLs - name: Analytics description: >- Read aggregated activity and usage metrics for your organization: compute minutes, workspaces created by source, and pull request throughput over a time range. - name: Presence description: >- Read and report ephemeral member presence: who is online, where they are (environment or workspace), and whether they are typing. Presence is backed by short-lived keys rather than the database and broadcast to other members over the events stream. - name: Plugins description: >- Install and manage native and Composio-backed workspace plugins. A plugin installs for a single environment, for the whole organization (which uses the Global environment), or for one member personally. A workspace uses the most specific installation available: personal, then its own environment, then the environment it was branched from, then Global. Composio Connect Links host managed OAuth, custom OAuth, API-key, bearer-token, basic, and dynamic OAuth authentication without exposing provider credentials to Replicas. paths: /v1/replica/{id}/messages: post: tags: - Replica summary: Send Message description: >- Sends a message to an existing replica. Supports targeting a specific chat, choosing a coding agent and model, attaching images, and enabling plan mode. operationId: sendReplicaMessage parameters: - name: id in: path description: The unique identifier of the replica required: true schema: type: string format: uuid requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/SendReplicaMessageRequest' responses: '200': description: Message accepted content: application/json: schema: $ref: '#/components/schemas/SendReplicaMessageResponse' '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '404': $ref: '#/components/responses/NotFound' '409': $ref: '#/components/responses/Conflict' '500': $ref: '#/components/responses/InternalServerError' '502': $ref: '#/components/responses/BadGateway' '503': $ref: '#/components/responses/ServiceUnavailable' security: - apiKey: [] - userJwt: [] - engineSecret: [] workspaceId: [] components: schemas: SendReplicaMessageRequest: type: object description: Request body for sending a message to a replica properties: message: type: string description: Message to send to the coding agent coding_agent: type: string description: Coding agent to use enum: - claude - codex - cursor - deepseek - fx - kimi - opencode - pi chat_id: type: string description: Target a specific chat session model: type: string description: >- Model to use for this message. DeepSeek Harness, Pi, and Opencode accept deepseek/deepseek-v4-pro-0813, deepseek/deepseek-v4-flash-0731, z-ai/glm-5.2, minimax/minimax-m3, xiaomi/mimo-v2.5-pro, and moonshotai/kimi-k2.6 through OpenRouter. fx and Kimi Code accept Vercel AI Gateway model slugs such as moonshotai/kimi-k2.6 and zai/glm-5.2. images: type: array items: $ref: '#/components/schemas/ImageContent' description: Images to attach to the message plan_mode: type: boolean description: >- Whether to run in plan mode. Leading `/plan` in the message is also detected and stripped. goal_mode: type: boolean description: >- Whether to set the message as the active Codex goal. Leading `/goal` in the message is also detected and stripped. fast_mode: type: boolean description: >- Whether to run in fast mode. Leading `/fast` in the message is also detected and stripped. thinking_level: type: string description: >- Thinking/reasoning level. Controls how much effort the agent puts into reasoning. `ultra` is Codex-only; `ultracode` is Claude Code-only. Falls back to provider default when omitted (Claude default: high, Codex default: medium, Cursor default: medium, DeepSeek Harness default: medium, Opencode default: medium, Pi default: medium). enum: - low - medium - high - xhigh - max - ultra - ultracode senderUserId: type: string description: >- Identifier of the user sending this message. When the request is authenticated via dashboard auth, the server overrides this with the authenticated user's id so team workspaces can attribute messages to the actual sender. senderEmail: type: string description: >- Email of the user sending this message. When the request is authenticated via dashboard auth, the server overrides this with the authenticated user's email. required: - message SendReplicaMessageResponse: type: object description: Response after sending a message to a replica properties: status: type: string description: Status of the message delivery enum: - sent - queued - waking message_id: type: - string - 'null' description: Unique identifier for the sent message position: type: - integer - 'null' description: Queue position if status is 'queued' chat_id: type: - string - 'null' description: ID of the chat the message was sent to required: - status - message_id - position - chat_id ImageContent: type: object description: An image attachment for messages properties: type: type: string const: image description: Content type, always 'image' source: type: object description: Image source data oneOf: - type: object properties: type: type: string const: base64 media_type: type: string enum: - image/png - image/jpeg - image/gif - image/webp description: MIME type of the image data: type: string description: Base64-encoded image data required: - type - media_type - data - type: object properties: type: type: string const: url url: type: string format: uri description: URL to the image required: - type - url required: - type - source Error: type: object properties: error: type: string description: Error message details: type: - string - 'null' description: Additional error details required: - error responses: BadRequest: description: Bad request - Missing or invalid parameters content: application/json: schema: $ref: '#/components/schemas/Error' Unauthorized: description: Unauthorized - Invalid or missing API key content: application/json: schema: $ref: '#/components/schemas/Error' NotFound: description: Resource not found content: application/json: schema: $ref: '#/components/schemas/Error' Conflict: description: >- Conflict - Resource already exists or operation conflicts with current state content: application/json: schema: $ref: '#/components/schemas/Error' InternalServerError: description: Internal server error content: application/json: schema: $ref: '#/components/schemas/Error' BadGateway: description: >- Bad gateway - The workspace is unreachable or returned an invalid response content: application/json: schema: $ref: '#/components/schemas/Error' ServiceUnavailable: description: >- Service unavailable - The service is temporarily overloaded or under maintenance content: application/json: schema: $ref: '#/components/schemas/Error' securitySchemes: apiKey: type: http scheme: bearer description: >- API key authentication. Obtain your API key from the Replicas dashboard under Organization → Settings → API Keys. userJwt: type: http scheme: bearer description: >- Logged-in user-session JWT authentication for first-party clients. Org-scoped requests also require the `Replicas-Org-Id` header. User JWTs cannot create workspaces with `POST /v1/replica`. engineSecret: type: http scheme: bearer description: Workspace engine secret used by agent-mode workspace requests. workspaceId: type: apiKey in: header name: X-Workspace-Id description: >- Workspace ID used with the engine secret for agent-mode workspace requests. ````