yelno.ai
ModelsGet API key
Model APIs / Images

Images

Generate images from a prompt. The response carries the images as base64 with their media type, plus the route and charge.

POST/v1/images/generationsinference:invokeBrowse image models →

Request

FieldRequiredNotes
modelrequiredAn image model's id from the catalog.
promptrequiredWhat to draw.
noptionalHow many images.
sizeoptionalRequested size, when the model takes one.
aspect_ratiooptionalFor models sized by ratio, e.g. "16:9".
quality · output_format · background · seedoptionalGeneration settings, applied as the model defines them.
input_referencesoptionalReference images: [{type: "image_url", image_url: {url}}].
Request
curl https://yelno.ai/v1/images/generations \
  -H "Authorization: Bearer $YELNO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MODEL",
    "prompt": "A lighthouse on a basalt cliff at dusk, watercolor",
    "n": 1,
    "aspect_ratio": "16:9"
  }'

Response

200 with the images as base64 and their media type — no hosted URL is returned.

200 · application/json
{
  "created": 1759572000,
  "data": [{ "b64_json": "iVBORw0KGgo…", "media_type": "image/png" }],
  "usage": { … },
  "yelno": {
    "request_id": "req_…",
    "provider": "…",
    "model": "…",
    "endpoint_id": "ep_…",
    "attempts": [ … ],
    "cost": { "state": "final", "currency": "USD", "customer_nanos": … }
  }
}

Every JSON response carries the same yelno block a chat response does: request_id, provider, model, endpoint_id, attempts and cost. cost is {state: "final", currency, customer_nanos} when the provider reported the cost with the response, or {state: "pending", currency, note} when it reports it later — the charge then settles once. Errors use the standard error envelope; upstream text never reaches you.

Notes

No streaming yet: the gateway returns the finished images in one response.

Sending a model to a route it is not served on answers 422 capability_unsupported with code: "operation_unsupported" and a message naming the route that serves it. Every model in the catalog shows its type and route.

Pricing. You pay the model's listed final price — shown on its catalog page — and nothing on top. A model without a fixed unit price is billed per request: its exact charge comes back with every response in yelno.cost. A hold is placed before dispatch and released down to the final charge; when the charge is reported after the response, the request settles once — it is never charged a guess.