GET

/v1/schemas/meta/image/v1%2Fimages%2Fgenerations

kind inputactivity imagehash 151c01c9…extracted Oct 27, 2026version currentsource upstream spec ↗

Request body

12 properties · 2 required · 1 $defs
propertytypedescriptionconstraints
model*stringModel ID for image generation.
prompt*stringText description of the images to generate.
nintegerNumber of images to generate. Range: 1-10. Defaults to 1. (minimum: 1, maximum: 10, default: 1)1 ≤ n ≤ 10 · default: 1
sizestringRequested image shape as width x height (e.g., '1024x1024'). The value is converted into an aspect ratio only; the image is produced at the generator's own fixed output resolution, so the returned pixel dimensions stay constant regardless of the numbers suppli…
response_formatenumFormat for returned images. One of: url, b64_json. Defaults to b64_json. (default: b64_json)url | b64_json
moderationstringModeration level for the safety pipeline. One of auto or low. Enabled per model: on models where it is not enabled, any moderation value returns 400 (code: unsupported_parameter, param: moderation); omitting moderation is always valid. On enabled models, unkno…
output_formatstringRequested file type for the generated images. One of png, jpeg, or webp. Defaults to webp when omitted; any other value is rejected.
reasoning_strengthenumHow much reasoning the image generator applies before producing the image. One of low or high. low returns after a single generation pass (no self-refinement); high (the default) lets the generator iteratively refine. (default: high)low | high
temperaturenumberSampling temperature for the model's planning step (prompt writing and refinement), between 0 and 2. It does not change how the image itself is sampled. Omit it to keep the model default. (minimum: 0, maximum: 2)0 ≤ n ≤ 2
userstringA stable end-user identifier that helps detect and mitigate abuse. Use it on the images endpoints; on the Responses and Chat Completions endpoints, use safety_identifier instead.
streambooleanIf true, streams the response as server-sent events. Defaults to false. (default: false)default: false
tool_enablementimage-tool-enablementPer-tool controls for the image generator's planner. Omit to keep the default (all tools available).

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"meta","endpointId":"v1/images/generations","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}