VisionStory OpenAPI
Get API key
Image Generation/Get Image Models
GET/api/v1/image/models

Machine-readable capabilities of available image models: aspect ratios, resolutions, reference image limits, and base price: credit_per_image at the default resolution, plus credit_by_resolution for every supported resolution (GPT Image models cost more at 2K). reference_pricing describes any surcharge added to that base: only GPT Image 2 charges 1 extra credit per additional group of up to 3 references after the first 6 (maximum 16). Null means no reference surcharge; GPT Image 2.5 models remain limited to 6 references.

Headers

X-API-KeystringRequired
Your VisionStory API key (sk-vs-...), kept server-side. Create one at OpenApi (Pro plan and up).

Response

200Successful Response

Successful calls return a standard envelope: the endpoint payload under data (its fields are documented below), plus a message string ("success") and an ISO 8601 server_time.

Response fields (data)
modelsarray of ImageModelDtoRequired
Machine-readable model capabilities, including credit_per_image
Show 6 propertiesHide 6 properties
model_idstringRequired
Public model ID to send in image-generation requests.
descriptionstringRequired
Public model summary.
credit_per_imageintegerRequired
Base credits per image before any reference surcharge, at the model's default resolution. Example prices illustrate the response only; query this endpoint for live pricing.
credit_by_resolutionobjectRequired
Base credits per image for each supported resolution, excluding reference surcharge. Some models (such as the GPT Image ones) cost more at 2K than at 1K; for the others every resolution has the same price.
reference_pricingImageReferencePricing | nullOptional
Reference surcharge added to base price: ceil(max(0, ref_count - included_refs) / refs_per_credit) * credit_per_step. Null means no surcharge.
Show 3 propertiesHide 3 properties
included_refsintegerRequired
Reference images included in the base price.
refs_per_creditintegerRequired
Additional references per surcharge step; round up partial steps.
credit_per_stepintegerRequired
Credits added per step, per generated image.
paramsImageModelParamsRequired
Allowed image parameters and defaults.
Show 4 propertiesHide 4 properties
promptImagePromptCapabilityRequired
Prompt-length limit.
Show 1 propertyHide 1 property
max_lengthintegerRequired
Maximum prompt characters for image generation or editing.
aspect_ratioStringChoicesRequired
Supported image aspect ratios and default.
Show 2 propertiesHide 2 properties
valuesarray of stringRequired
Currently accepted values for this model.
defaultstring | nullRequired
Value used when the request omits this parameter.
resolutionStringChoicesRequired
Supported output sizes and default.
Show 2 propertiesHide 2 properties
valuesarray of stringRequired
Currently accepted values for this model.
defaultstring | nullRequired
Value used when the request omits this parameter.
refsImageReferencesRequired
Reference-image count and accepted kinds.
Show 2 propertiesHide 2 properties
maxintegerRequired
Maximum reference images per request.
acceptarray of stringRequired
Accepted reference kinds; currently image.

Errors

All error responses share one JSON envelope: an error object with a numeric code, a human-readable message, an optional details string, and an optional hint giving an actionable next step (handy for AI agents).

errorErrorDetailRequired
Error payload returned with every non-2xx response. Present only on failure; successful calls use the standard success envelope instead.
Show 4 propertiesHide 4 properties
codeintegerRequired
Machine-readable error code. Mirrors the HTTP status for transport-level failures (e.g. 401, 404, 422, 500) and may carry a business-specific code otherwise.
messagestringRequired
Human-readable explanation of what went wrong. Safe to log or surface to end users; not localized.
detailsstring | nullOptional
Optional structured detail about the failure, e.g. a JSON string of per-field validation errors on a 422. Absent when there is nothing extra to report.
hintstring | nullOptional
Actionable next step for resolving the error, written for both humans and AI agents (e.g. how to fix the request, or where to obtain an API key). May be absent.