falText to textComing soon

openrouter/router/decisions

Name: openrouter/router/decisions
Brand: fal

openrouter/router/decisions is a text to text tool from fal that runs in the background and returns text. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Price pending

Pricing

Price pending.

Limits

Runs: In the background
Returns: text
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`state` required	JSON	—	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.
`image_urls`	URLs or files	—	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` required	JSON	—	Questions keyed by caller-defined IDs. Each question is evaluated independently against the same state.
`model`	text	typesafe/jev-1.13	Any OpenRouter Decisions model ID or alias. Choose a model that supports the supplied input modalities.
`session_id`	text	—	Identifier for grouping related decision requests.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "openrouter/router/decisions",
    "input": {
      "state": {},
      "questions": {}
    }
  }'