Loading API documentation
Make typed decisions over text, structured state, or multimodal content.
The client provides a convenient way to interact with the model API.
npm install --save @fal-ai/clientThe @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Install the new package and update your imports — see client setup.
Set FAL_KEY as an environment variable in your runtime.
export FAL_KEY="YOUR_API_KEY"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: {
instructions: "Is the customer requesting a refund?",
type: "noul"
},
department: {
instructions: "Which team should handle this request?",
criteria: {
shipping: "Delivery status, delays, or lost packages",
billing: "Charges, invoices, or payment problems",
returns: "Refunds, exchanges, or damaged items"
},
type: "choice"
}
}
},
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);The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.
import { fal } from "@fal-ai/client";
fal.config({
credentials: "YOUR_FAL_KEY"
});When running code on the client-side (e.g. in a browser, mobile app or GUI applications), make sure to not expose your FAL_KEY. Instead, use a server-side proxy to make requests to the API. For more information, check out our server-side integration guide.
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: {
instructions: "Is the customer requesting a refund?",
type: "noul"
},
department: {
instructions: "Which team should handle this request?",
criteria: {
shipping: "Delivery status, delays, or lost packages",
billing: "Charges, invoices, or payment problems",
returns: "Refunds, exchanges, or damaged items"
},
type: "choice"
}
}
},
webhookUrl: "https://optional.webhook.url/for/results",
});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,
});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);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.
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.
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.
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);The client will auto-upload the file for you if you pass a binary object (e.g. File, Data).
Read more about file handling in our file upload guide.
Text, structured JSON, or an array mixing text strings with OpenRouter media parts: image_url, input_audio, and video_url. Images and videos use base64 data URLs; input_audio uses raw base64 data and a format. Media support and limits depend on the selected Decisions model. See https://openrouter.ai/docs/guides/community/multimodal-decisions.
Optional image URLs or base64 image data URLs appended to state. Public images are downloaded and encoded inline for OpenRouter. Inline images are limited to 16 MiB per image. Up to 128 convenience images and 32 MiB of total encoded image data (including data URL metadata) are allowed per request. The selected Decisions model must support images.
Questions keyed by caller-defined IDs. Each question is evaluated independently against the same state.
model stringAny OpenRouter Decisions model ID or alias. Choose a model that supports the supplied input modalities. Default value: "typesafe/jev-1.13"
session_id stringIdentifier for grouping related decision requests.
enable_safety_checker booleanAuthorized callers may set false to request relaxed screening. Default value: true
{
"state": "My card was charged twice. Please refund the duplicate.",
"questions": {
"refund_requested": {
"instructions": "Is the customer requesting a refund?",
"type": "noul"
},
"department": {
"instructions": "Which team should handle this request?",
"criteria": {
"shipping": "Delivery status, delays, or lost packages",
"billing": "Charges, invoices, or payment problems",
"returns": "Refunds, exchanges, or damaged items"
},
"type": "choice"
}
},
"model": "typesafe/jev-1.13",
"enable_safety_checker": true
}model string* requiredid stringprovider string{
"model": "",
"usage": {}
}input_tokens integer* requiredoutput_tokens integer* requiredtotal_tokens integercost floattype string* requirednoul float* requiredProbability from 0 to 1 that the answer is yes.
type string* requiredThe yes/no question, as text or structured multimodal content.
Optional descriptions clarifying true and false outcomes.
type string* requiredThe question, as text or structured multimodal content.
Answer options mapped to descriptions of each option.
type string* requiredThe property to score, as text or structured multimodal content.
Ordered level descriptions, from the low end to the high end.
What should count as a yes/true outcome.
What should count as a no/false outcome.