Recraft V4 Pro - Kyma API

Overview

This is a text-to-image model from Recraft that outputs at 4MP resolution. It shares the same underlying design aesthetic as the base V4 model but scales up for print-ready, poster, and hero campaign use cases. Kyma serves it through an OpenAI-compatible endpoint with automatic request failover. The model supports prompt caching, which bills repeated prompt prefixes at this model’s cached input rate. Exact generation costs are returned in the usage.cost field, and the X-Kyma-Model header confirms which model executed the request. It accepts text input and produces images only. It does not support vision, reasoning, or structured outputs. Generation operates at a medium speed tier and uses premium per-image pricing.

Specs

Field	Value
Model ID	`recraft-v4-pro`
Best for	Print, posters, hero campaign, large displays
Context window	0
Input modalities	Text
Output modalities	Image
Tool calling	Yes
Structured outputs	Yes
Prompt caching	Yes
Speed	Medium
Cost band	Premium
Release stage	Stable

Pricing

	Per 1M tokens
Input	$0.20
Output	$0.60

Use this when

Print-ready marketing assets — Generate high-resolution posters and brochures for physical distribution.
Large-scale display graphics — Create hero images and digital billboards that scale without pixelation.
Brand-consistent design work — Maintain Recraft V4’s aesthetic while producing larger output files.
Campaign visual production — Produce multiple high-resolution variants for coordinated marketing pushes.

Not ideal for

Do not use this model for low-latency web prototyping, mobile-optimized thumbnails, or tasks requiring image understanding or structured data extraction.

Pick something else when

You need faster generation for web or mobile screens: use recraft-v4 or flux-1.1-ultra.
You need vector graphics for scalable logos: use recraft-v4-vector-pro.
You need lower-cost batch generation for drafts: use imagen-4-fast or flux-2-pro.

Example

from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="ky-...")

response = client.chat.completions.create(
    model="recraft-v4-pro",
    messages=[{"role": "user", "content": "..."}],
)

Agent query example

Ask the API which models fit, instead of hardcoding an id:

curl "https://kymaapi.com/v1/models?recommended_for=generate-images&tools=true&quality_tier=frontier-open"

FAQ

Does this model support image-to-image or vision tasks? No, it only accepts text prompts and outputs images. How does prompt caching affect billing? Repeated prompt prefixes are billed at this model’s cached input rate. What happens if a generation path degrades? Kyma automatically reroutes the request to a healthy serving path without requiring manual retries.

​Overview

​Specs

​Pricing

​Use this when

​Not ideal for

​Pick something else when

​Example

​Agent query example

​FAQ