Instances
Send Message
Send a message to an instance and get a response from the AI agent.
POST
Send a message to a running OpenClaw instance. Chowder proxies your request to the instance’s gateway, which processes it through the OpenResponses API — an open-source implementation of the OpenAI Responses API format. The instance must be inDocumentation Index
Fetch the complete documentation index at: https://docs.chowder.dev/llms.txt
Use this file to discover all available pages before exploring further.
running status. If it’s stopped or provisioning, you’ll get a 409 Conflict.
Accepts an organization key (
chd_org_*) or a scoped key (chd_sk_*) with interact permission on this instance.Path Parameters
The ID of the instance to send a message to.
Request Body
The body follows the OpenAI Responses API format. At minimum you needmodel and input.
The model to use for this request. This is passed through to the configured model provider — use model identifiers like
"claude-sonnet-4-20250514", "gpt-4o", or "gemini-2.0-flash" depending on which provider the instance is set up with.The user message to send. This is the text input for the AI agent.
instructions, tools, previous_response_id for conversation continuity). These are passed through to the gateway as-is.
Response
Returns200 OK with the OpenResponses API response object.
Unique response ID (e.g.
"resp_abc123"). Use this as previous_response_id in follow-up messages to maintain conversation context.Always
"response".Response status, typically
"completed".Array of output items. Each item has a
type field. The most common type is "message", which contains the agent’s reply.The model that generated the response.
Token usage for the request.
Conversation Continuity
To have a multi-turn conversation, pass theid from the previous response as previous_response_id in your next request: