OpenRouter / Chat completion

OpenRouter tool openrouter-chat on looot: input fields, $0.000006 per result, output shape, and code to run it with curl, JavaScript or Python.

Runs a chat completion on one of 15 current models (OpenAI GPT-6 Luna and GPT-5.4, Gemini 3.8 Flash, DeepSeek v4, Qwen 3.8, GLM 5.3, Kimi K2.6, Mistral Small, Grok). messages is the usual [{role, content}] list; max_tokens (1-16000) is required and caps the answer (reasoning tokens count toward it). Returns choices[0].message.content and usage with the exact cost. OpenAI-compatible request and response.

Tool id: openrouter-chat
Provider: OpenRouter
Job: Completion llm chat (llm.chat.completion)
Price: $0.000006 per result. A call that fails at the provider costs $0.

Inputs

Name	Type	Required	Description
`max_tokens`	integer	yes
`messages`	array	yes
`model`	string	yes
`response_format`	object	no	e.g. {“type”:“json_object”} or a json_schema
`seed`	integer	no
`stop`	array	no
`temperature`	number	no
`top_p`	number	no

Output

The run’s result holds the provider’s answer. Signed in, looot inspect openrouter-chat prints its fields.

Run it

Every call needs your API token in LOOOT_TOKEN; Sign in shows how to get one. Each run also needs a new idempotency key, so a retry never pays twice. With wait: 30 the answer comes back inline when the run ends within 30 seconds. Otherwise you get the running run back: poll GET /v1/runs/<runId>.

Example input with placeholder values:

curl -X POST "https://api.looot.ai/v1/runs" \
  -H "Authorization: Bearer $LOOOT_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"endpointId":"openrouter-chat","input":{"model":"<model>","messages":[],"max_tokens":1},"wait":30}'

const response = await fetch("https://api.looot.ai/v1/runs", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.LOOOT_TOKEN}`,
    "Content-Type": "application/json",
    "Idempotency-Key": crypto.randomUUID(),
  },
  body: JSON.stringify({
    endpointId: "openrouter-chat",
    input: {
      model: "<model>",
      messages: [],
      max_tokens: 1,
    },
    wait: 30,
  }),
});
const run = await response.json();
console.log(run.status, run.result);

import os
import uuid

import requests

response = requests.post(
    "https://api.looot.ai/v1/runs",
    headers={
        "Authorization": f"Bearer {os.environ['LOOOT_TOKEN']}",
        "Idempotency-Key": str(uuid.uuid4()),
    },
    json={
        "endpointId": "openrouter-chat",
        "input": {
            "model": "<model>",
            "messages": [],
            "max_tokens": 1,
        },
        "wait": 30,
    },
    timeout=90,
)
run = response.json()
print(run["status"], run.get("result"))

To let looot pick among every provider of this job instead, send job:llm.chat.completion as endpointId; see the job page.