GetLLM — Unified AI gateway & memory layer

Chat

The Chat API (/v1/bot/*) is the assistant layer: it queries Memory, calls the model, persists the turn, and streams the reply — the same engine the GetLLM web Chat runs on. Sessions hold the transcript; you only send the next message.

Base path

https://www.getllm.ai/v1/bot

Same host and same gl-live-... key as the gateway — only the path prefix differs.

Create an API key Back to gateway docs

Chat API — a hosted chat backend (BaaS)

Building a chat product? The /v1/bot/* surface is the same backend that powers our own Chat page — sessions, streaming, long-term memory, image/video generation, and sharing as hosted APIs, so your app ships a UI instead of infrastructure.

/v1/bot/sessions — persistent transcripts with rename/share/archive; messages are stored server-side.
use_memory: true recalls the user's long-term memory into the prompt and ingests new facts after each turn.
/v1/bot/generate-image and async /v1/bot/generate-video + job polling, billed like any other usage.
/v1/webhook delivers signed generation events to your server.

# create a session (management key)
curl -X POST https://www.getllm.ai/v1/bot/sessions   -H "Authorization: Bearer gl-mgmt-..." -d '{}'

# stream a reply with memory (live key; SSE)
curl -N https://www.getllm.ai/v1/bot/chat   -H "Authorization: Bearer gl-live-..."   -d '{"session_id":"<id>","message":"hi","use_memory":true}'

Full request/response shapes are in the API reference; the cookbook has an end-to-end recipe.

Chat, Image & Video

Streaming chat with memory

# Omit session_id to start a new session (its id arrives in the first event)
curl https://www.getllm.ai/v1/bot/chat \
  -H "Authorization: Bearer gl-live-..." \
  -H "Content-Type: application/json" \
  -d '{"message":"hi — remember my name is Sam","model":"gpt-4o"}'
# Server-Sent Events: event: session → delta chunks → event: done

Generate images & video

# Image generation is synchronous — returns the stored assistant message
curl https://www.getllm.ai/v1/bot/generate-image \
  -H "Authorization: Bearer gl-live-..." \
  -H "Content-Type: application/json" \
  -d '{"prompt":"a red panda coding at night"}'

# Video generation is async — submit, then poll the job
curl https://www.getllm.ai/v1/bot/generate-video \
  -H "Authorization: Bearer gl-live-..." \
  -H "Content-Type: application/json" \
  -d '{"prompt":"a timelapse of a city at dusk"}'
# → { "job_id": "...", "status": "processing" }  —  poll /v1/bot/video-jobs/{id}

Manage conversations with /v1/bot/sessions (list / create / get / rename / delete). Attachments use /v1/bot/upload-ticket. See the API Reference for full schemas.