Gemini 3.5 Flash 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 \
  -H "Authorization: Key $MRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": "Think carefully and thoroughly, then answer: design a rate limiter for a multi-tenant API. Compare token bucket, leaky bucket, sliding window log and sliding window counter across accuracy, memory, burst behaviour and distributed coordination. Then recommend one and justify it in about 400 words."
      }
    ],
    "max_tokens": 8000,
    "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/requests/$REQUEST_ID/status" \
  -H "Authorization: Key $MRUN_API_KEY"
curl "https://queue.modelrunner.run/google/gemini-3.5-flash/requests/$REQUEST_ID" \
  -H "Authorization: Key $MRUN_API_KEY"

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

const result = await modelrunner.subscribe("google/gemini-3.5-flash", {
  input: {
    "messages": [
      {
        "role": "user",
        "content": "Think carefully and thoroughly, then answer: design a rate limiter for a multi-tenant API. Compare token bucket, leaky bucket, sliding window log and sliding window counter across accuracy, memory, burst behaviour and distributed coordination. Then recommend one and justify it in about 400 words."
      }
    ],
    "max_tokens": 8000
  },
});
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",
    headers=headers,
    json={
      "messages": [
        {
          "role": "user",
          "content": "Think carefully and thoroughly, then answer: design a rate limiter for a multi-tenant API. Compare token bucket, leaky bucket, sliding window log and sliding window counter across accuracy, memory, burst behaviour and distributed coordination. Then recommend one and justify it in about 400 words."
        }
      ],
      "max_tokens": 8000
    },
).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