falImage to textComing soon

openrouter/router/vision

Name: openrouter/router/vision
Brand: fal

openrouter/router/vision is an image 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
`image_urls`	URLs or files	—	List of image URLs to be processed.
`pdf_urls`	list	—	List of PDF document URLs to be processed. Only PDF files are accepted: http(s) URLs must point to a .pdf file and data URIs must be data:application/pdf;base64,... Models without native PDF support fall back to OpenRouter's document parsing.
`prompt` required	text	—	Prompt to be used for the image
`system_prompt`	text	—	System prompt to provide context or instructions to the model
`model` required	text	—	Name of the model to use. Charged based on actual token usage.
`reasoning`	true or false	false	Should reasoning be the part of the final answer.
`temperature`	number 0 to 2	1	This setting influences the variety in the model's responses. Lower values lead to more predictable and typical responses, while higher values encourage more diverse and less common responses. At 0, the model always gives the same response for a given input.
`max_tokens`	number (whole) 1 to …	—	This sets the upper limit for the number of tokens the model can generate in response. It won't produce more than this limit. The maximum value is the context length minus the prompt length.
`enable_web_search`	true or false	false	Give the model access to real-time web information via OpenRouter's web search server tool. When enabled, the model decides when to search and may search multiple times per request. Search costs are charged in addition to token usage.
`web_search_options`	JSON	—	Options for web search (engine, result limits, domain filters, ...). Ignored unless enable_web_search is true.

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/vision",
    "input": {
      "prompt": "Caption this image for a text-to-image model with as much detail as possible.",
      "model": "openai/gpt-6-sol"
    }
  }'