Explore documentation
  1. Welcome to AI SRE 👋
  2. AI SRE vs MCP server
  3. Customize AI SRE
  4. Writing code
    1. Creating pull requests for errors
    2. Bulk resolving errors
  5. Analyzing data
    1. Analyzing incidents
    2. Analyzing logs
    3. Checking for outliers
  6. Managing data
    1. Creating dashboards
    2. Importing Datadog dashboards
    3. Importing Grafana dashboards
  7. Integrations
    1. Linear
    2. Sentry
    3. Datadog
    4. Grafana
    5. GitHub
    6. Notion
  8. AI SRE API
    1. Getting an API token
    2. Chats API
      1. List all chats GET
      2. Get a single chat GET
      3. Create a chat POST
      4. Get chat status GET
      5. Reply to a chat POST
      6. Approve or deny a confirmation PATCH
      7. Remove a chat DELETE
    3. List models GET

Reply to a chat

Posts your next message to an existing chat and starts the next agent turn. The request returns as soon as the message is saved. Poll the chat status until it leaves processing, then get the chat to read the answer.

POST https://chat.betterstack.com/api/v2/chats/{chat_id}/messages

URL parameters

chat_id
required string

The ID of the chat to reply to.

Headers

Authorization
required string

Bearer $TOKEN

Content-Type
required string

application/json

Body parameters

message
required string

Your message to the agent.

model
string

Switches the chat to another model from List models. If omitted, the chat keeps its current model.

201

Returns the chat, still processing. Its transcript ends with your message and a placeholder for the agent's answer.

Response body

{
  "data": {
    "id": "12345",
    "type": "chat",
    "attributes": {
      "team_id": 123456,
      "team_name": "example-team",
      "name": "Checkout 5xx spike",
      "status": "processing",
      "message_count": 4,
      "last_message_at": "2026-09-07T10:35:00.000Z",
      "total_tokens": 15420,
      "model": "anthropic/claude-opus-5.5",
      "total_cost_usd": 0.0928,
      "created_at": "2026-09-07T10:30:00.000Z",
      "updated_at": "2026-09-07T10:35:00.000Z",
      "messages": [
        {
          "id": 9001,
          "message_type": "user",
          "text": "Why did checkout start returning 5xx at 10:15?",
          "artifacts": [],
          "created_at": "2026-09-07T10:30:00.000Z",
          "user": null
        },
        {
          "id": 9002,
          "message_type": "ai",
          "text": "The 5xx responses come from checkout-api pods restarting after the 10:12 deploy of v2.4.0. The new version fails its readiness probe because PAYMENTS_URL is unset. Set it in the deployment manifest and roll out again.",
          "artifacts": [],
          "created_at": "2026-09-07T10:32:18.000Z",
          "user": null
        },
        {
          "id": 9003,
          "message_type": "user",
          "text": "Was the payments service affected too?",
          "artifacts": [],
          "created_at": "2026-09-07T10:35:00.000Z",
          "user": null
        },
        {
          "id": 9004,
          "message_type": "ai",
          "text": null,
          "artifacts": [],
          "created_at": "2026-09-07T10:35:00.000Z",
          "user": null
        }
      ],
      "pending_confirmations": []
    }
  }
}
400

Bad Request - Model Not Available

Response body

{
  "errors": "The requested model is not available. Use one of available_models; GET /api/v2/chats/models describes the models a chat can run on.",
  "available_models": [
    "deepseek/deepseek-v4.1-flash",
    "openai/gpt-5.6-sol",
    "anthropic/claude-opus-5.5"
  ]
}
401

Unauthorized

Response body

{
  "errors": "Invalid authentication"
}
403

Forbidden - AI SRE Not Included In Your Plan

Response body

{
  "errors": "AI SRE is not available on this plan."
}
404

Not Found

Response body

{
  "errors": "Resource with the provided ID was not found"
}
409

Conflict - The Agent Is Still Working

Response body

{
  "errors": "The agent is still working on this chat (status: processing). Poll GET /api/v2/chats/:id/status and retry once it leaves processing."
}
409

Conflict - A Confirmation Is Pending

Response body

{
  "errors": "The agent is waiting on a tool-use confirmation (status: awaiting_confirmation). Resolve it via PATCH /api/v2/chats/:chat_id/confirmations/:id before replying."
}
422

Unprocessable Entity - Missing Required Attributes

Response body

{
  "errors": "Sorry, you are missing some required attributes",
  "required_attributes": [
    "message"
  ]
}
422

Unprocessable Entity - Model Can't Be Switched

Response body

{
  "errors": "Sorry, some values are incorrect",
  "invalid_values": {
    "model": "can't be changed on a chat created before model selection"
  }
}

Example cURL

Example
curl --request POST \
  --url https://chat.betterstack.com/api/v2/chats/12345/messages \
  --header "Authorization: Bearer $TOKEN" \
  --header 'Content-Type: application/json' \
  --data '{
    "message": "Was the payments service affected too?"
  }'


Previous article

Get chat status

Next article

Approve or deny a confirmation