Chat & Completions

OpenAI-compatible chat completions with automatic memory context injection and model listing.

`POST /v1/chat/completions`

Executes a chat completion session. Supports standard OpenAI message formats, streaming Server-Sent Events (stream: true), and automatic memory context injection.

Scope Required: chat
Rate Limit: 60 req/min (per key), 600 req/hr (per principal)

Request Headers

Authorization: Bearer omni_sk_live_...
Content-Type: application/json
X-Omni-Workspace: ws_123 (optional)

Request Body

{
  "model": "gpt-4o-mini",
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "Tell me about my recent notes." }
  ],
  "stream": true,
  "temperature": 0.7,
  "memory": {
    "enabled": true,
    "limit": 5
  }
}

Response Headers

X-Omni-Shimmer: Memory injection status (injected, skipped, no-context).
X-Omni-Memory-Count: Number of memories injected into the context.
X-Omni-Notes-Count: Number of workspace notes injected.

`GET /v1/models`

Lists curated LLM models available on the platform.

Scope Required: chat

Request

curl -sS "https://edge.omnistatic.com/v1/models" \
  -H "Authorization: Bearer $OMNI_API_KEY"

Response

{
  "object": "list",
  "data": [
    { "id": "gpt-4o", "object": "model", "owned_by": "openai" },
    { "id": "gpt-4o-mini", "object": "model", "owned_by": "openai" },
    { "id": "claude-sonnet-4-5", "object": "model", "owned_by": "anthropic" },
    { "id": "gemini-3-flash-preview", "object": "model", "owned_by": "google" },
    { "id": "deepseek-chat", "object": "model", "owned_by": "deepseek" }
  ]
}