OpenAI-compatible text-to-image (x402 or API-key paid)

OpenAI Images API shape — point an OpenAI-compatible client at this base URL and image generation works unmodified. model accepts LivePair image model ids (see models in GET /v1/agent/models); unknown ids return 400 rather than silently swapping models. size maps to aspect ratio (1024x1024→1:1, 1792x1024→16:9, 1024x1792→9:16); LivePair extension fields aspectRatio/resolution/imageSize are honored when the model advertises them. Synchronous up to ~100s — past that the response is the standard {status:'running',jobId,poll} handoff; a submitted job that fails later provider-side is not un-charged.

post/v1/agent/images/generations

Request

  • Base URL: https://livepairai.com (the document declares no server; this is the origin it was published from)
  • URL: https://livepairai.com/v1/agent/images/generations
  • Auth: one of:
    • API key in header x-api-key
    • HTTP bearer
    • none

Request body

promptstring required

Image prompt, <=2000 chars

modelstring

LivePair image model id — omit for the catalog default (qwen-image-3)

size'1024x1024' | '1792x1024' | '1024x1792' | '1536x1024' | '1024x1536'
nnumber

Only 1 supported

response_format'url' | 'b64_json'
aspectRatiostring
resolutionstring
imageSizestring
payerstring

Your payer wallet — applies your volume-tier discount (5% at $100+, 10% at $500+, 15% at $2000+ lifetime paid). Must equal the wallet that signs the payment.

Response

OpenAI images response — {created, data:[{url} | {b64_json}]} (or {status:'running',jobId,poll} past the sync window)

creatednumber
dataobject[]

Changes

No recorded changes to this operation across all 1 revision of this API.