Send message.

post

https://app.customgpt.ai/api/v1/projects/{projectId}/conversations/{sessionId}/messages

Sends a user message to an agent and returns the agent's response. Supports streaming for real-time display, file attachments for document analysis, and persona overrides for dynamic behavior. This is the primary endpoint for chat interactions.

Notes: Add ?stream=true to receive the response in real-time chunks.

Recent Requests

Time	Status	User Agent
Retrieving recent requests…

Loading…

Path Params

projectId

integer

required

The ID of the agent to get the messages for

sessionId

string

required

The session ID of the converstaions to get the messages for

Query Params

stream

boolean

Defaults to false

When true, the response is sent as a stream of data-only server-sent events (SSE) as tokens are generated, terminated by a status: "finish" event. When false, the full response is returned in a single JSON object. See the streaming guide for client implementation examples.

lang

string

Defaults to en

The ISO 639-1 language code for the response language. Examples: es — Spanish, fr — French, de — German, ja — Japanese. The agent will attempt to respond in this language regardless of the query language.

external_id

string

length ≤ 128

The external ID of the prompt history.

Body Params

Send a message to a conversation.

prompt

string

Prompt to send to OpenAI

custom_persona

string | null

Custom persona to use for the conversation

chatbot_model

string | null

enum

Agent model to use for the conversation

response_source

string | null

enum

Defaults to default

By default, we ask ChatGPT to use only your content in its response (recommended). If you wish ChatGPT to improvise and use its own knowledgebase as well, you can set this to "openai_content".

Allowed:

custom_context

string | null

Custom context to use for the conversation

file

file | null

File to upload (Allowed types: pdf, docx, doc, odt, txt, jpg, jpeg, png, webp)

files[]

array of files | null

Multiple files to upload (Allowed types: pdf, docx, doc, odt, txt, jpg, jpeg, png, webp)

files[]

agent_capability

string | null

enum

Defaults to optimal-choice

Agent capability to use for the conversation.

Allowed:

labels[]

array | null

Optional source-label filter. Accepts two formats: (1) Flat array of label IDs or names for OR semantics, e.g. ["A","B","C"]. (2) Array of arrays for AND/OR logic (inner=OR, outer=AND), e.g. [["A","B"],["C","D"]] means (A OR B) AND (C OR D). Max 20 groups, 50 labels per group, 500 total. Invalid values are ignored.

labels[]

labels_exclusive

boolean

Defaults to false

If true, search only pages with provided labels. If false, search pages with provided labels plus unlabeled pages.

Responses

200Send a message to a conversation

400Bad Argument

401API Token is either missing or invalid

404Agent not found

429Resource Exhausted when sending a message to a conversation

500Internal Server Error