Try H3 Max Director
Log-inSign-up
Contact SalesLog-inSign-up

openrouter/router/decisions

Run any decision model with fal, powered by OpenRouter.
Inference
Commercial use
Partner
Schema
LLMs
PlaygroundAPI

Table of contents

About

Make typed decisions over text or structured state with OpenRouter.

1. Calling the API#

Install the client#

The client provides a convenient way to interact with the model API.

npm install --save @fal-ai/client

Setup your API Key#

Set FAL_KEY as an environment variable in your runtime.

export FAL_KEY="YOUR_API_KEY"

Submit a request#

The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("openrouter/router/decisions", {
  input: {
    state: "My card was charged twice. Please refund the duplicate.",
    questions: {
      refund_requested: {
        type: "noul",
        instructions: "Is the customer requesting a refund?"
      },
      department: {
        type: "choice",
        criteria: {
          shipping: "Delivery status, delays, or lost packages",
          returns: "Refunds, exchanges, or damaged items",
          billing: "Charges, invoices, or payment problems"
        },
        instructions: "Which team should handle this request?"
      }
    }
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

2. Authentication#

The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.

API Key#

In an environment where you cannot set environment variables, you can configure the API key manually on the client.
import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

3. Queue#

Submit a request#

The client API provides a convenient way to submit requests to the model.

import { fal } from "@fal-ai/client";

const { request_id } = await fal.queue.submit("openrouter/router/decisions", {
  input: {
    state: "My card was charged twice. Please refund the duplicate.",
    questions: {
      refund_requested: {
        type: "noul",
        instructions: "Is the customer requesting a refund?"
      },
      department: {
        type: "choice",
        criteria: {
          shipping: "Delivery status, delays, or lost packages",
          returns: "Refunds, exchanges, or damaged items",
          billing: "Charges, invoices, or payment problems"
        },
        instructions: "Which team should handle this request?"
      }
    }
  },
  webhookUrl: "https://optional.webhook.url/for/results",
});

Fetch request status#

You can fetch the status of a request to check if it is completed or still in progress.

import { fal } from "@fal-ai/client";

const status = await fal.queue.status("openrouter/router/decisions", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
  logs: true,
});

Get the result#

Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.

import { fal } from "@fal-ai/client";

const result = await fal.queue.result("openrouter/router/decisions", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);

4. Files#

Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.

Data URI (base64)#

You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.

Hosted files (URL)#

You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.

Uploading files#

We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.

import { fal } from "@fal-ai/client";

const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);

Read more about file handling in our file upload guide.

5. Schema#

Input#

state string | object | list<void>* required

Text or structured JSON content for the model to evaluate.

questions Questions* required

Questions keyed by caller-defined IDs. Each question is evaluated independently against the same state.

model string

OpenRouter Decisions model to use. Default value: "typesafe/jev-1.13"

session_id string

Identifier for grouping related decision requests.

{
  "state": "My card was charged twice. Please refund the duplicate.",
  "questions": {
    "refund_requested": {
      "type": "noul",
      "instructions": "Is the customer requesting a refund?"
    },
    "department": {
      "type": "choice",
      "criteria": {
        "shipping": "Delivery status, delays, or lost packages",
        "returns": "Refunds, exchanges, or damaged items",
        "billing": "Charges, invoices, or payment problems"
      },
      "instructions": "Which team should handle this request?"
    }
  },
  "model": "typesafe/jev-1.13"
}

Output#

model string* required
answers Answers* required
usage DecisionsUsage* required
id string
provider string
{
  "model": "",
  "usage": {}
}

Other types#

UsageInfo#

prompt_tokens integer
completion_tokens integer
total_tokens integer
cost float* required
prompt_tokens_details PromptTokensDetails

OpenAIEmbeddingsRequest#

DecisionsNoulCriteria#

true string | object | list<void>* required

What should count as a yes/true outcome.

false string | object | list<void>* required

What should count as a no/false outcome.

DecisionsChoiceAnswer#

type string* required
choice string* required
confidence float
probabilities object

WebSearchUserLocation#

type string

Location type. Only 'approximate' is supported. Default value: "approximate"

city string

City name, e.g. 'San Francisco'.

region string

Region or state, e.g. 'California'.

country string

Two-letter country code, e.g. 'US'.

timezone string

IANA timezone, e.g. 'America/Los_Angeles'.

OpenAIChatCompletionsRequest#

DecisionsScoreAnswer#

type string* required
score float* required
confidence float
probabilities object
legend object

PromptTokensDetails#

cached_tokens integer
cache_write_tokens integer

DecisionsNoulQuestion#

type string* required
instructions string* required

The yes/no question to evaluate.

criteria DecisionsNoulCriteria

Optional descriptions clarifying true and false outcomes.

WebSearchOptions#

engine EngineEnum

Search engine to use. 'auto' uses native provider search when available and falls back to Exa. 'native' prefers the provider's built-in web search (OpenAI, Anthropic, Google, xAI, Perplexity), falling back to Exa for models without native support. 'exa' always uses Exa's search API. Default value: "auto"

Possible enum values: auto, native, exa

max_results integer

Maximum results per search call (1-25). Applies to the Exa engine; ignored with native provider search. Defaults to 5.

max_uses integer

Maximum number of searches the model may perform in a single request. Once reached, further search calls return an error result instead of executing. With native provider search, forwarded only to Anthropic; other native providers ignore it.

max_total_results integer

Maximum total results across all search calls in a single request. Useful for controlling cost and context size in agentic loops.

search_context_size Enum

How much content to retrieve per result. For Exa: low=5K, medium=15K, high=30K characters per result; when omitted, Exa picks adaptively (~2-4K per result). Ignored with native provider search. Overridden by max_characters when both are set.

Possible enum values: low, medium, high

max_characters integer

Exact maximum characters of content per result (1-100,000). Applies to the Exa engine; ignored with native provider search. Takes precedence over search_context_size when both are set.

allowed_domains list<string>

Limit results to these domains. Supported by Exa and most native providers (not Google native search).

excluded_domains list<string>

Exclude results from these domains. Supported by Exa and some native providers (not OpenAI or Google native search).

user_location WebSearchUserLocation

Approximate user location for location-biased results. Only supported by native provider search; ignored by Exa.

OpenAIResponsesRequest#

OpenAIEmbeddingsResponse#

DecisionsChoiceQuestion#

type string* required
instructions string* required

The question the model should answer.

criteria Criteria* required

Answer options mapped to descriptions of each option.

DecisionsNoulAnswer#

type string* required
noul float* required

Probability from 0 to 1 that the answer is yes.

DecisionsScoreQuestion#

type string* required
instructions string* required

The quality or property to score.

criteria list<string | object | list<void>>* required

Ordered level descriptions, from the low end to the high end.

DecisionsUsage#

input_tokens integer* required
output_tokens integer* required
total_tokens integer
cost float

OpenAIResponsesResponse#

OpenAIChatCompletionsResponse#

Related Models