POST
Llm Generate
Run a single-turn BRAHMA-30B completion. POST /api/voice/llm/generate All requests authenticate with your PeachDesk API key in the X-API-Key header (an interactive session token in Authorization: Bearer also works тАФ see Authentication). Use the playground to send a live request and inspect the response.

Authorizations

X-API-Key
string
header
required

Organization API key (bibha_...). Takes precedence over the session credential, and is refused outright on user-session-only and super-admin routes.

Body

application/json

Request model for LLM text generation.

prompt
string
required
Required string length: 1 - 50000
system
string | null
Maximum string length: 4000
model_size
string | null
default:BRAHMA-30B-FP8
Pattern: ^(BRAHMA-30B-FP8)$
max_tokens
integer
default:512
Required range: 1 <= x <= 4096
temperature
number
default:0.7
Required range: 0 <= x <= 2
examples
string[][] | null
Maximum array length: 8

Response

Successful Response

Response model for LLM text generation.

text
string
required
model_size
string
required
usage
UsageInfo ┬╖ object | null

Per-request resource usage the engine reports back to the API proxy.

The proxy meters/bills off these fields; each one maps to a rate-registry unit (TTS per character, STT per audio-second, LLM per token). Only the dimensions relevant to the request are populated тАФ the rest stay None.