Gemini 3.5 Flash-Lite API

# Submit a request to the queue. Input fields go at the top level of the
# body. The optional reserved "metadata" object holds your own flat string
# tags — stored on the request, never sent to the model; filter later with
# GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>.
curl -X POST https://queue.modelrunner.run/google/gemini-3.5-flash-lite \
  -H "Authorization: Key $MRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": "Extract the order details as JSON with keys order_id, customer, items (array of {name, qty, unit_price}), and total. Text: Order #A-8842 for Dana Whitfield: 3x cold brew concentrate at 12.50 each, 1x ceramic pour-over at 34.00, 2x filter pack at 6.25. Charged 105.00 to card ending 4417."
      }
    ],
    "max_tokens": 4000,
    "response_format": {
      "type": "json_object"
    },
    "metadata": {
      "project": "my-project"
    }
  }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }

# Poll status_url until "COMPLETED", then fetch the result
curl "https://queue.modelrunner.run/google/gemini-3.5-flash-lite/requests/$REQUEST_ID/status" \
  -H "Authorization: Key $MRUN_API_KEY"
curl "https://queue.modelrunner.run/google/gemini-3.5-flash-lite/requests/$REQUEST_ID" \
  -H "Authorization: Key $MRUN_API_KEY"

import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("google/gemini-3.5-flash-lite", {
  input: {
    "messages": [
      {
        "role": "user",
        "content": "Extract the order details as JSON with keys order_id, customer, items (array of {name, qty, unit_price}), and total. Text: Order #A-8842 for Dana Whitfield: 3x cold brew concentrate at 12.50 each, 1x ceramic pour-over at 34.00, 2x filter pack at 6.25. Charged 105.00 to card ending 4417."
      }
    ],
    "max_tokens": 4000,
    "response_format": {
      "type": "json_object"
    }
  },
});
console.log(result);

import os
import requests

headers = {"Authorization": f"Key {os.environ['MRUN_API_KEY']}"}

submitted = requests.post(
    "https://queue.modelrunner.run/google/gemini-3.5-flash-lite",
    headers=headers,
    json={
      "messages": [
        {
          "role": "user",
          "content": "Extract the order details as JSON with keys order_id, customer, items (array of {name, qty, unit_price}), and total. Text: Order #A-8842 for Dana Whitfield: 3x cold brew concentrate at 12.50 each, 1x ceramic pour-over at 34.00, 2x filter pack at 6.25. Charged 105.00 to card ending 4417."
        }
      ],
      "max_tokens": 4000,
      "response_format": {
        "type": "json_object"
      }
    },
).json()

# Poll submitted["status_url"] until "COMPLETED", then:
result = requests.get(submitted["response_url"], headers=headers).json()

Input parameters

{
  "mcpServers": {
    "modelrunner": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.modelrunner.run/mcp"]
    }
  }
}

claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcp