Chats

Post a message to an existing chat and stream the reply

Changed on

Sends a message or resumes pending tool approvals and streams the assistant reply. Earlier messages are included automatically. To approve or deny tools, send approvals: [{ "id": "<approvalId>", "approved": true }] for every pending approval in the latest assistant message, without a message field; use "approved": false to deny. Approval IDs are emitted in tool-approval-request chunks and stored on tool parts in chat history.

post/v1/chats/{chatId}

Request

  • Base URL: https://api.usenotra.com
  • URL: https://api.usenotra.com/v1/chats/{chatId}
  • Auth: HTTP bearer

Path parameters

chatIdstring required
Example:chat_abc123

Request body

messagestring

The user message to send.

model'auto' | 'anthropic/claude-opus-5.5' | 'anthropic/claude-opus-5' | 'anthropic/claude-opus-4.8' | 'anthropic/claude-sonnet-5' | 'anthropic/claude-sonnet-4.6' | 'anthropic/claude-haiku-4.5' | 'openai/gpt-6-sol' | 'openai/gpt-6-luna' | 'openai/gpt-5.6-sol' | 'openai/gpt-5.5' | 'openai/gpt-5.4'

Model to respond with. Defaults to auto, which lets Notra choose.

enableThinkingboolean

Allow the model to reason before answering.

thinkingLevel'off' | 'low' | 'medium' | 'high'

How much reasoning effort to spend when thinking is enabled.

timezonestring

IANA time zone used to interpret dates in the conversation.

Example request

{
  "message": "Summarize what shipped in the last week.",
  "model": "auto",
  "thinkingLevel": "medium",
  "timezone": "Europe/Berlin"
}

Response

Streaming UI message stream (newline-delimited JSON chunks). Read the X-Chat-Id response header for the chat id, or take it from the start chunk's messageMetadata.chatId.

Changes

  • 1400c1e9b5d8Revision changes
    • info

      added the new optional request property

    • info

      the request property became optional

    • info

      added the new anthropic/claude-opus-5.5 enum value to the request property

    • info

      added the new openai/gpt-5.6-sol enum value to the request property

    • info

      added the new openai/gpt-6-luna enum value to the request property

    • info

      added the new openai/gpt-6-sol enum value to the request property

    • info

      added the non-success response with the status

  • d29720a5c9f1Revision changes
    • breaking

      added the new required request property /

    • breaking

      the request property type changed from no type to object

    • warning

      removed subschema #2 from the request property allOf list

    • info

      added the new optional request property /