Image tools tools

Image toolsimage_to_prompt

Image to prompt

Extract Chinese and English image prompts, keywords and structured prompts from an image.

Start with your agent

Claude CodeCodexCursor

Download and install the dedicated Mouter Skill for “Image to prompt”: https://mouter.ai/skills/image_to_prompt.zip

Pricing

How credits work

0.02 credits per call

Usage example

Agent

Example input

Use image_to_prompt. Analyze this reference image and extract Chinese and English generation prompts, its aspect ratio and key visual elements: <image URL> Confirm inputs and estimated cost before running.

Example output

Example only: Image to prompt has not been run. Once a task succeeds, its result contains these fields:

  1. titletext
  2. aspect_ratiotext
  3. keywordslist
  4. zh_prompttext
  5. en_prompttext
  6. structured_promptobject
  7. notestext

Values depend on your input. The matching JSON example structure is in the API tab.

  • Getting started: provide image URL.

FAQ

Which inputs does this tool accept?

The live schema lists the required fields, accepted values and constraints. Check it before submitting; your agent can read it for you.

Can I use this with an agent or API?

Yes. Use the dedicated Skill or connect your agent to the MCP endpoint. The API example uses MCP over HTTP with your Mouter API key.

How is this tool billed?

The Pricing section lists the current rate, with billing units and variant rates where they apply. Final charges use the executing account’s rates and actual usage.