> ## Documentation Index > Fetch the complete documentation index at: https://docs.decimal.app/llms.txt > Use this file to discover all available pages before exploring further. # Send a message > Send a message to get an AI-powered response. Omit `conversation_id` to start a new conversation, or provide one to continue an existing conversation. Returns `202 Accepted` immediately. The AI processes in the background. Poll `GET /v0/chat/{conversation_id}` until `status` is `completed`. ## OpenAPI ````yaml /openapi-v0.yaml post /v0/chat openapi: 3.1.0 info: title: Decimal Chat API version: v0 description: > ## Authentication All endpoints require a Bearer token: ``` Authorization: Bearer sk-de-... ``` API tokens are created in the Decimal dashboard under Settings → API Tokens. Each token has scopes that control access: `chat:read`, `chat:write`, `chat:escalate`. ## Quick Start ```bash # 1. Send a message curl -X POST https://api.getdecimal.ai/v0/chat \ -H "Authorization: Bearer sk-de-..." \ -H "Content-Type: application/json" \ -d '{"message": "How do I configure SSO?"}' # → 202 { "conversation_id": "abc123", "status": "processing" } # 2. Poll until complete curl https://api.getdecimal.ai/v0/chat/abc123 \ -H "Authorization: Bearer sk-de-..." # → 200 { "status": "completed", "messages": [...] } ``` ### Continue a conversation ```bash curl -X POST https://api.getdecimal.ai/v0/chat \ -H "Authorization: Bearer sk-de-..." \ -H "Content-Type: application/json" \ -d '{"message": "Can you show me the SAML setup?", "conversation_id": "abc123"}' ``` ## Rate Limiting Every response includes rate limit headers: - `X-RateLimit-Limit` — Requests allowed per minute - `X-RateLimit-Remaining` — Requests remaining in current window - `X-RateLimit-Reset` — Unix timestamp when the window resets Rate limits apply at two levels: - **Per API token:** 120 requests/min - **Per organization:** 600 requests/min across all tokens The stricter limit applies. Headers report the per-token limit. Contact support for higher limits. contact: name: Decimal Support url: https://getdecimal.ai servers: - url: https://api.getdecimal.ai description: Production - url: http://localhost:3000 description: Local development security: - BearerAuth: [] tags: - name: Chat description: >- Send messages and get AI-powered answers from your public knowledge base and code. - name: Escalation description: Escalate conversations to external ticketing integrations. - name: Utility description: Token introspection. paths: /v0/chat: post: tags: - Chat summary: Send a message description: > Send a message to get an AI-powered response. Omit `conversation_id` to start a new conversation, or provide one to continue an existing conversation. Returns `202 Accepted` immediately. The AI processes in the background. Poll `GET /v0/chat/{conversation_id}` until `status` is `completed`. operationId: sendMessage requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/SendMessageRequest' examples: newConversation: summary: Start a new conversation value: message: How do I configure SSO? continueConversation: summary: Continue existing conversation value: message: Can you show me the SAML setup? conversation_id: abc123 responses: '202': description: Message accepted for processing. headers: X-RateLimit-Limit: $ref: '#/components/headers/X-RateLimit-Limit' X-RateLimit-Remaining: $ref: '#/components/headers/X-RateLimit-Remaining' X-RateLimit-Reset: $ref: '#/components/headers/X-RateLimit-Reset' content: application/json: schema: $ref: '#/components/schemas/ChatAccepted' '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '403': $ref: '#/components/responses/Forbidden' '404': description: Conversation not found (when `conversation_id` is provided). content: application/json: schema: $ref: '#/components/schemas/Error' '409': $ref: '#/components/responses/Conflict' '429': $ref: '#/components/responses/RateLimited' '500': $ref: '#/components/responses/InternalError' security: - BearerAuth: - chat:write components: schemas: SendMessageRequest: type: object properties: message: type: string minLength: 1 maxLength: 16000 description: The user's message. conversation_id: type: string description: >- Omit to start a new conversation. Provide to continue an existing conversation. required: - message ChatAccepted: type: object properties: conversation_id: type: string description: Conversation ID. Use this to poll or continue the conversation. status: type: string enum: - processing required: - conversation_id - status Error: type: object properties: error: type: object properties: code: type: string enum: - bad_request - unauthorized - forbidden - not_found - conflict - rate_limited - internal_error description: Machine-readable error code. message: type: string description: Human-readable error message. retryable: type: boolean description: Whether the client should retry the request. required: - code - message required: - error headers: X-RateLimit-Limit: description: Maximum requests allowed per minute. schema: type: integer X-RateLimit-Remaining: description: Requests remaining in the current window. schema: type: integer X-RateLimit-Reset: description: Unix timestamp when the rate limit window resets. schema: type: integer responses: BadRequest: description: Invalid request body or parameters. content: application/json: schema: $ref: '#/components/schemas/Error' Unauthorized: description: Missing or invalid API key. content: application/json: schema: $ref: '#/components/schemas/Error' Forbidden: description: Valid API key but insufficient scope. content: application/json: schema: $ref: '#/components/schemas/Error' Conflict: description: >- Resource state conflict (e.g., conversation still processing, already escalated). content: application/json: schema: $ref: '#/components/schemas/Error' RateLimited: description: Rate limit exceeded. headers: X-RateLimit-Limit: $ref: '#/components/headers/X-RateLimit-Limit' X-RateLimit-Remaining: $ref: '#/components/headers/X-RateLimit-Remaining' X-RateLimit-Reset: $ref: '#/components/headers/X-RateLimit-Reset' Retry-After: description: Seconds until the rate limit resets. schema: type: integer content: application/json: schema: $ref: '#/components/schemas/Error' InternalError: description: Unexpected server error. content: application/json: schema: $ref: '#/components/schemas/Error' securitySchemes: BearerAuth: type: http scheme: bearer description: | API token with `sk-de-` prefix. Created in the Decimal dashboard under Settings → API Tokens. ````