> ## Documentation Index > Fetch the complete documentation index at: https://developer.happenstance.ai/llms.txt > Use this file to discover all available pages before exploring further. # Send Chat Message > Send a message to a chat started through the API. Returns at once with the turn to poll. A message sent while a turn is still working joins that turn (joined: true): Chat takes it into the work in progress, and the turn's reply and charge cover both messages. When a turn ends with stop_reason needs_input, Chat waits on the questions in its reply.questions: send answers (by question index and option label), a message that answers them in words, or both. The answer starts the next turn (answered: true). Returns 402 when the balance is below 3 credits for this message and for each turn still running, 409 for a chat started in the app. ## OpenAPI ````yaml /openapi.json post /v1/chat/{chat_id}/messages openapi: 3.1.0 info: title: Happenstance API description: > The Happenstance API provides programmatic access to network search, person research and Happenstance Chat. ## Authentication All API endpoints require authentication using an API key. Include your API key in the `Authorization` header: ``` Authorization: Bearer YOUR_API_KEY ``` ## Error Responses All errors follow RFC 7807 Problem Details format with `application/problem+json` content type. Example error response: ```json { "type": "https://developer.happenstance.ai/errors/empty-field", "title": "Bad Request", "status": 400, "detail": "Description must not be empty", "instance": "/v1/research" } ``` version: 0.1.0 servers: - url: https://api.happenstance.ai description: Production security: [] paths: /v1/chat/{chat_id}/messages: post: summary: Send Chat Message description: >- Send a message to a chat started through the API. Returns at once with the turn to poll. A message sent while a turn is still working joins that turn (joined: true): Chat takes it into the work in progress, and the turn's reply and charge cover both messages. When a turn ends with stop_reason needs_input, Chat waits on the questions in its reply.questions: send answers (by question index and option label), a message that answers them in words, or both. The answer starts the next turn (answered: true). Returns 402 when the balance is below 3 credits for this message and for each turn still running, 409 for a chat started in the app. operationId: send_chat_message_v1_chat__chat_id__messages_post parameters: - name: chat_id in: path required: true schema: type: string title: Chat Id requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/SendChatMessageRequestV1' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/SendChatMessageResponseV1' '400': description: Bad Request content: application/json: schema: $ref: '#/components/schemas/ProblemDetailV1' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ProblemDetailV1' '402': description: Payment Required content: application/json: schema: $ref: '#/components/schemas/ProblemDetailV1' '403': description: Forbidden content: application/json: schema: $ref: '#/components/schemas/ProblemDetailV1' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/ProblemDetailV1' '410': description: Gone content: application/json: schema: $ref: '#/components/schemas/ProblemDetailV1' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/ProblemDetailV1' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/ProblemDetailV1' '503': description: Service Unavailable content: application/json: schema: $ref: '#/components/schemas/ProblemDetailV1' security: - HTTPBearer: [] components: schemas: SendChatMessageRequestV1: properties: message: anyOf: - type: string - type: 'null' title: Message description: >- The message to send, in plain text. While Chat waits on its questions (a turn with stop_reason needs_input), a message answers them in words. answers: anyOf: - items: $ref: '#/components/schemas/ChatAnswerV1' type: array - type: 'null' title: Answers description: >- Answers to Chat's open questions, one per question you answer. Send answers, a message, or both (the message then adds to the answers). additionalProperties: false type: object title: SendChatMessageRequestV1 SendChatMessageResponseV1: properties: chat_id: type: string title: Chat Id description: The chat's id url: type: string title: Url description: The chat in the Happenstance app turn_id: type: string title: Turn Id description: >- The turn to poll: the one this message started, or the running turn it joined status: type: string enum: - queued - running - completed - failed - cancelled title: Status description: The turn's status joined: type: boolean title: Joined description: >- True when the message joined the turn that was still running: Chat takes it into that turn's work, and the turn's reply and charge cover both messages default: false answered: type: boolean title: Answered description: True when the message or answers answered Chat's open questions default: false warning: anyOf: - type: string - type: 'null' title: Warning description: Warning message when credit balance is low additionalProperties: false type: object required: - chat_id - url - turn_id - status title: SendChatMessageResponseV1 description: Response from POST /v1/chat/{chat_id}/messages. ProblemDetailV1: properties: type: type: string title: Type description: A URI reference that identifies the problem type default: >- https://developer.happenstance.ai/api-reference/introduction#error-response-format title: type: string title: Title description: A short, human-readable summary of the problem status: type: integer title: Status description: The HTTP status code detail: anyOf: - type: string - type: 'null' title: Detail description: A human-readable explanation specific to this occurrence instance: anyOf: - type: string - type: 'null' title: Instance description: >- A URI reference that identifies the specific occurrence of the problem additionalProperties: false type: object required: - title - status title: ProblemDetailV1 description: RFC 7807 Problem Details for HTTP APIs ChatAnswerV1: properties: question_index: type: integer minimum: 0 title: Question Index description: The question's index, from 0 selected: items: type: string type: array maxItems: 4 title: Selected description: >- The chosen option labels, exactly as given (several only for a multi_select question) other: anyOf: - type: string maxLength: 32000 - type: 'null' title: Other description: A free-text answer instead of or beside the options additionalProperties: false type: object required: - question_index title: ChatAnswerV1 description: >- An answer to one of Chat's questions (reply.questions of a needs_input turn). securitySchemes: HTTPBearer: type: http scheme: bearer ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.