Skip to main content
POST
/
v1
/
lexi
/
chat
/
stream
Stream Chat with Lexi
curl --request POST \
  --url https://api.example.com/v1/lexi/chat/stream \
  --header 'Content-Type: application/json' \
  --data '
{
  "message": "<string>",
  "conversation_id": "<string>",
  "context": {},
  "allow_tools": true
}
'
This endpoint consumes AI credits (typically 1 - 5 credits per request depending on tool usage). If the workspace balance is insufficient, the API returns 402 insufficient_credits immediately, before any events are streamed.

​
Request

This is the streaming counterpart to POST /v1/lexi/chat. The response is a text/event-stream that emits incremental events as Lexi reasons through the prompt and uses tools. Because the request is a POST, you must use a fetch-based SSE client - the browser’s EventSource only supports GET.

​
Headers

Authorization: Bearer wbk_your_api_key_here
Content-Type: application/json
Accept: text/event-stream
​
Idempotency-Key
string
Optional UUID to deduplicate retries within 24 hours. Credits are charged only on the first successful stream.

​
Body Parameters

​
message
string
required
User message to send to Lexi. Maximum 12,000 characters.
​
conversation_id
string
Optional conversation UUID. When omitted, a new conversation is created and its ID is emitted in the first text event’s conversation_id metadata.
​
context
object
Optional page / entity context: contact_id, deal_id, matter_id, company_id, page.
​
allow_tools
boolean
default:"true"
When false, Lexi will not invoke any CRM tools and will respond purely from the conversation context.

​
Event Types

EventPurpose
thinkingIntermediate reasoning step. Payload: data: {"text": "..."}. Safe to ignore if not rendering a progress UI.
tool_stepLexi is about to invoke or has completed a CRM tool. Payload: data: {"tool": "...", "status": "started" or "completed", "summary": "..."}.
textIncremental assistant text. Payload: data: {"delta": "...", "conversation_id": "..."}. Concatenate delta values to build the final response.
doneFinal event with usage metadata. Payload: data: {"credits_remaining": 4840, "message_id": "msg_01HY1"}.
The stream terminates with the literal line data: [DONE] followed by a newline, consistent with the OpenAI SSE convention.

​
Response Format

event: thinking
data: {"text": "Looking up the contact in your pipeline..."}

event: tool_step
data: {"tool": "contacts.get", "status": "started"}

event: tool_step
data: {"tool": "contacts.get", "status": "completed", "summary": "Found 1 contact"}

event: text
data: {"delta": "Jane Doe is currently", "conversation_id": "conv_01HY1"}

event: text
data: {"delta": " in the Proposal stage...", "conversation_id": "conv_01HY1"}

event: done
data: {"credits_remaining": 4840, "message_id": "msg_01HY1"}

data: [DONE]
Responses include X-RateLimit-Limit, X-RateLimit-Remaining, X-RateLimit-Reset, and X-Request-ID headers on the initial HTTP response. 
curl -N -X POST \
  https://data.leadlex.com/functions/v1/api-gateway/v1/lexi/chat/stream \
  -H "Authorization: Bearer wbk_your_api_key_here" \
  -H "Content-Type: application/json" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Summarize my pipeline",
    "conversation_id": null
  }'

​
Errors

StatusCodeDescription
400validation_errorMissing message, or prompt exceeds size limit
401invalid_keyInvalid or expired API key
402insufficient_creditsWorkspace credit balance is exhausted
403insufficient_permissionsMissing write:ai permission
404conversation_not_foundSupplied conversation_id does not exist
429rate_limitedRate limit exceeded
Errors surface as a single event: error in the SSE stream when they occur after the HTTP headers have been sent, with the same code / message payload as JSON responses. Clients should therefore handle both HTTP-level and in-stream error events.