Imagen 4 Fast - Kyma API

Overview

Imagen 4 Fast is a text-to-image model from Google that generates photorealistic and multi-style visuals. It operates in a fast, cheap tier that prioritizes generation speed over maximum fidelity. On Kyma, it accepts text prompts and returns images. It supports prompt caching, and requests are routed through an OpenAI-compatible endpoint with automatic failover if a serving path degrades. Usage responses include exact costs in usage.cost and report the running model via the X-Kyma-Model header. This model does not support vision input, structured outputs, or reasoning. Token limits do not apply to this text-to-image workflow. Use it for quick visual drafts rather than final production assets requiring high detail.

Specs

Field	Value
Model ID	`imagen-4-fast`
Best for	Rapid iteration, drafts, social previews
Context window	0
Input modalities	Text
Output modalities	Image
Tool calling	Yes
Structured outputs	Yes
Prompt caching	Yes
Speed	Fast
Cost band	Cheap
Release stage	Stable

Pricing

	Per 1M tokens
Input	$0.20
Output	$0.60

Use this when

Rapid Concept Drafting — Quickly generate placeholder visuals during early design phases.
Social Media Previews — Produce fast, multi-style images for content scheduling and testing.
High-Volume Generation — Scale image creation workflows where speed and cost efficiency matter more than maximum detail.

Not ideal for

Do not use this tier for final production assets or workflows that require high-fidelity detail, vision input, or structured output parsing.

Pick something else when

You need maximum image fidelity and detail: use imagen-4-ultra.
You require vector graphics or design-ready assets: use recraft-v4-vector.
You need high-quality photorealism with advanced prompt control: use 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="imagen-4-fast",
    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=strong"

FAQ

Does Imagen 4 Fast support image-to-image or vision inputs? No, it only accepts text prompts and outputs images. It does not support vision input or reasoning. How does prompt caching affect my costs? Kyma bills repeated prompt prefixes at this model’s cached input rate, which applies here since the model supports caching. Do I need separate API keys or handle routing manually? No, Kyma uses one API key for every model and handles automatic failover if a serving path degrades.

​Overview

​Specs

​Pricing

​Use this when

​Not ideal for

​Pick something else when

​Example

​Agent query example

​FAQ