Model Overview

gpt-image-2-text-to-image

GPT Image 2 image generation model.

imagetask

Pricing

Per Call$ 0.07 / image

Public pricing comes from the currently exposed Xenodia model catalog and already reflects the minimum visible channel pricing.

Answer-first summary

Use this model when you need a public Xenodia surface with discoverable parameters, stable routing metadata, and documented request modes instead of provider-specific guesswork.

Recommended workflow: query /v1/models, inspect this model's capabilities, then call the relevant endpoint with only documented fields.

curl -s https://api.xenodia.xyz/v1/models

Capabilities

Brand: openai
Upstream ID: gpt-image-2-text-to-image
Async support: Yes
Request modes: task
Reference input: Public URL + File upload · max 16

Supported parameters

promptrequired

Text instruction for the image generation task.

aspect_ratio

Documented in model discovery.

auto1:19:1616:94:33:4

resolution

Optional GPT Image-2 resolution. With aspect_ratio auto, only 1K is valid; aspect_ratio 1:1 cannot be used with 4K.

1K2K4K

async

Compatibility flag. Image generation always returns a Xenodia task object for polling.

Reference input rules

Transport: url, multipart_file
Field names: image_input, image, image[], image_input[]
Max items: 16
Accepted MIME: image/jpeg, image/png, image/webp

FAQ

What can gpt-image-2-text-to-image do on Xenodia?

gpt-image-2-text-to-image is exposed through Xenodia as a public model page with pricing, modalities, parameters, and documented request modes.

Does gpt-image-2-text-to-image support async tasks?

gpt-image-2-text-to-image supports async task mode through Xenodia's public task resource.