MiniMax Image 01 - Kyma API

Overview

MiniMax Image 01 is a text-to-image generator built by MiniMax. It accepts text prompts and outputs images across five standard aspect ratios: 1:1, 16:9, 9:16, 4:3, and 3:4. It operates on a flat per-image billing structure, making it the most economical option available on the platform. The model runs on Kyma’s OpenAI-compatible endpoints with automatic failover, so degraded serving paths are rerouted without dropping requests. Prompt caching is supported, billing repeated prefixes at this model’s cached input rate. Usage metadata, including exact cost, is returned in the response, and the active model is reported via the X-Kyma-Model header. It does not support vision, reasoning, or structured outputs. It is strictly a text-to-image pipeline. While it delivers strong quality for its tier, it is not designed for photorealistic precision or complex multi-step generation tasks.

Specs

Field	Value
Model ID	`minimax-image-01`
Best for	Bulk image generation, social shorts, stock-style assets, budget UI mockups
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

Bulk Social Media Assets — Generate large batches of platform-optimized images for short-form video thumbnails and posts.
Budget UI Mockups — Rapidly produce placeholder graphics and layout assets during early-stage design sprints.
Stock-Style Illustrations — Create generic, reusable visual assets for documentation, blogs, and marketing collateral.
High-Volume Prototyping — Test prompt variations and iterate quickly without incurring high per-request costs.

Not ideal for

Do not use this model when you require photorealistic fidelity, complex compositional control, or multi-modal reasoning capabilities.

Pick something else when

You need photorealistic detail and complex scene composition: use flux-2-pro or imagen-4-ultra.
You require vector graphics or scalable design assets: use recraft-v4-vector or recraft-v4-vector-pro.
You need fast, high-quality image editing or variations: use flux-kontext-pro or recraft-v4.

Example

from openai import OpenAI

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

response = client.chat.completions.create(
    model="minimax-image-01",
    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 this model support image-to-image or vision inputs? No, it only accepts text prompts and outputs images. For vision or image editing, use a model with vision or editing support. How does Kyma handle request routing for this model? Every request includes automatic failover. If a serving path degrades, Kyma reroutes the request to maintain reliability. Can I cache prompts to reduce costs? Yes, prompt caching is supported. Repeated prompt prefixes are billed at this model’s cached input rate.

​Overview

​Specs

​Pricing

​Use this when

​Not ideal for

​Pick something else when

​Example

​Agent query example

​FAQ