> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kymaapi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# FLUX 1.1 Pro Ultra

> FLUX 1.1 Pro Ultra is a legacy text-to-image model from bfl, optimized for cinematic photography, hero shots, and editorial layouts. Route new projects to newer alternatives, but use this model to maintain existing pipelines that depend on its specific output style.

## Overview

This is a text-to-image generation model from bfl that accepts text prompts and returns image outputs. It operates in a balanced cost tier with medium generation speed and is classified as a frontier-quality model. The model does not support vision input, reasoning, or structured outputs.

On Kyma, requests run through an OpenAI-compatible endpoint at [https://kymaapi.com/v1](https://kymaapi.com/v1) using a single API key for all models. Every request gets automatic failover if a serving path degrades, and responses include exact billing details in the usage.cost field. The X-Kyma-Model header reports the exact model that ran.

The model is marked as legacy and does not support multi-reference inputs or the quality improvements found in newer versions. It bills per image rather than per token, and prompt caching bills repeated prompt prefixes at this model's cached input rate. For new integrations, the platform recommends moving to a successor model that offers lower costs and expanded reference capabilities.

## Specs

| Field              | Value                                 |
| ------------------ | ------------------------------------- |
| Model ID           | `flux-1.1-ultra`                      |
| Best for           | Cinematic photo, hero shot, editorial |
| Context window     | 0                                     |
| Input modalities   | Text                                  |
| Output modalities  | Image                                 |
| Tool calling       | Yes                                   |
| Structured outputs | Yes                                   |
| Prompt caching     | Yes                                   |
| Speed              | Medium                                |
| Cost band          | Balanced                              |
| Release stage      | Stable                                |

## Pricing

|        | Per 1M tokens |
| ------ | :-----------: |
| Input  |     \$0.20    |
| Output |     \$0.60    |

## Use this when

* **Cinematic Photo Generation** — Generate high-fidelity cinematic stills from descriptive text prompts.
* **Editorial Layout Creation** — Produce polished editorial and magazine-style imagery for design workflows.
* **Hero Shot Production** — Render standalone hero images for web and marketing assets.
* **Legacy Pipeline Maintenance** — Maintain existing image generation workflows that rely on this specific model version.

## Not ideal for

Do not use this model for new projects requiring multi-reference inputs, faster generation speeds, or lower per-image costs.

## Pick something else when

* You need lower cost and higher quality: use [`flux-2-pro`](/models/flux-2-pro).
* You need faster generation speeds: use [`imagen-4-fast`](/models/imagen-4-fast).

## Example

```python theme={null}
from openai import OpenAI

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

response = client.chat.completions.create(
    model="flux-1.1-ultra",
    messages=[{"role": "user", "content": "..."}],
)
```

## Agent query example

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

```bash theme={null}
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 reference inputs?**

No, it only accepts text prompts and does not support vision or multi-reference inputs.

**How does Kyma handle pricing for this model?**

It bills per generated image, and prompt caching bills repeated prompt prefixes at this model's cached input rate.

**Is this model still actively recommended for new projects?**

No, it is classified as legacy, and newer projects should use updated alternatives for better performance and cost efficiency.