GMI Router Overview

​

How routing works

1. Understand. The router reads your latest message and classifies the task and its requirements.
2. Compare. It scores the allowed model pool across quality, cost, and latency.
3. Validate. The top candidate is checked before it is committed. A high score alone does not win the request.
4. Select. The router locks in the winning model.
5. Respond. The selected model generates the completion, returned inline or streamed token by token.

​

Authentication

​

Quick start: Autoroute

curl -X POST https://console.gmicloud.ai/api/v1/ie/recommendation/autoroute \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      { "role": "user", "content": "Summarize this contract in three bullet points." }
    ],
    "mode": "balanced",
    "stream": false
  }'

{
  "model": "provider/model-name",
  "message": { "role": "assistant", "content": "..." },
  "routing_metadata": {
    "selected_model": "provider/model-name",
    "task_type": "summarization",
    "selected_mode": "balanced",
    "fallback_models": ["provider/backup-a"],
    "recommendation_id": "bab0a8bb-195f-49c5-8f9c-016da0d89cc8"
  }
}

​

Request fields

​

Streaming vs non-streaming

• Streaming (default). Returns text/event-stream. Chunks are proxied as they arrive, followed by a routing_metadata event, then [DONE]. One backup model may be tried before the first token on a 5xx, provider error, 429, or a 10-second first-token timeout. Once tokens start flowing, no further fallback happens; a mid-stream failure keeps the partial output, sends an error event, and closes the stream.
• Non-streaming (stream: false). Returns one JSON object, trying the primary model plus one backup on a transient failure (5xx, provider error, 429), with a combined timeout of 10 minutes for primary and backup.

​

Status codes