How to Use FLUX.1 Kontext Max in Codex
Use FLUX.1 Kontext Max for image edits where wording, typography, and consistency need closer attention. Compared with FLUX.1 Kontext Pro, it emphasizes following detailed instructions and rendering text.
Prompts to try with FLUX.1 Kontext Max in Codex
Copy an example into Codex, or ask in your own words.
Use FLUX.1 Kontext Max to edit the storefront image in the project's assets. Replace 'COMING SOON' with 'NOW OPEN' while preserving the sign's position, lettering style, and surrounding facade.
Generate a product photo with FLUX.1 Kontext Max: a matte black water bottle on wet slate, soft morning light, 1:1. Tell me the price first. Save the result in ./assets.
Make four logo concepts for a coffee brand called "Northline" with FLUX.1 Kontext Max.
Create a 16:9 hero image of a quiet mountain cabin at dusk with FLUX.1 Kontext Max.
Generate a 9:16 poster with FLUX.1 Kontext Max for a jazz night called "Blue Hour", deep navy and brass tones.
How to set up FLUX.1 Kontext Max in Codex
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
codex mcp add spiral --url https://api.spiral.ai/mcp
- Sign in
Codex opens the browser: sign in to Spiral and click Authorize. No API key. codex mcp list then shows Spiral.
codex mcp login spiral
Use the Spiral skill
- Send Codex this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run FLUX.1 Kontext Max
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "fal", "model": "fal-ai/flux-pro/kontext/max", "input": { "prompt": "Put a donut next to the flour.", "image_url": "https://v3.fal.media/files/rabbit/rmgBxhwGYb2d3pl3x9sKf_output.png" } }'
Then paste one of the prompts above: Codex finds FLUX.1 Kontext Max on Spiral, shows the price and runs it.
FLUX.1 Kontext Max providers and prices
Spiral runs FLUX.1 Kontext Max through fal. Open a card for today's price, with every fee included.
Settings you can ask for
FLUX.1 Kontext Max works from your prompt and image URL. Ask Codex for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | The same seed and the same prompt given to the same version of the model will output the same image every time. | |
| Guidance scale (CFG) | 1 to 20 | 3.5 | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. |
| Number of images | 1 to 4 | 1 | The number of images to generate. |
| Output format | jpeg or png | jpeg | The format of the generated image. |
| Safety tolerance | 1 to 6 | 2 | The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. |
| Enhance prompt | on or off | off | Whether to enhance the prompt for better results. |
| Aspect ratio | 21:9, 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16 and 1 more | The aspect ratio of the generated image. |
Every API field of FLUX.1 Kontext [max] · Editing is on its tool page: open its card above.
What can you do with FLUX.1 Kontext Max in Codex?
Turn project briefs into illustrations, product concepts, and other image assets with FLUX.1 Kontext. A coding agent can use the project's content to write specific visual requests and compare results with the intended design.
Product color studies
Start with a product image and change one object's color. Specify the shape, material, lighting, and background that should remain.
Campaign scene changes
Move a photographed subject into a different setting while asking to preserve its appearance. Compare important details with the original.
Sign and label revisions
Replace wording in an existing sign, poster, or label while retaining its surrounding design. Check spelling and placement in the result.
Character storyboard frames
Use a character reference to develop scenes for a storyboard. Request preservation of facial features, hairstyle, and clothing, then inspect continuity between frames.
More on FLUX.1 Kontext Max and Codex
Overview
FLUX.1 Kontext Max in other agents
Questions about FLUX.1 Kontext Max in Codex
Can Codex use FLUX.1 Kontext Max?
Yes. Add Spiral to Codex as an MCP server, and Codex can find and run FLUX.1 Kontext Max like any built-in tool.
How much does FLUX.1 Kontext Max cost in Codex?
$0.104 per image. Billed on `num_images`, default 1. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Codex plan is separate.
Do I need a fal account to use FLUX.1 Kontext Max in Codex?
No. Spiral runs FLUX.1 Kontext Max on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up FLUX.1 Kontext Max in Codex?
About two minutes: add the hosted server, then sign in.
Does Codex wait while FLUX.1 Kontext Max runs?
FLUX.1 Kontext Max runs in the background. Codex starts the run, checks on it and gives you the image when it's ready.
When should I choose Pro or Max?
Choose Pro for iterative visual work and a balance of speed and quality. Choose Max when typography and following detailed instructions carry more weight.
What resolution does FLUX.1 Kontext produce?
Outputs are approximately 1 megapixel. A square text-to-image result defaults to 1024 by 1024 pixels; a wider or taller shape changes the dimensions within roughly that pixel budget.
Can FLUX.1 Kontext make illustrations as well as realistic images?
Yes. Describe the intended medium, such as a photograph, pencil illustration, or painting, along with the subject and composition.
Can I rely on every word in an image being correct?
Review the result before using it. Max emphasizes typography, but FLUX.1 Kontext can still miss specific instructions.
What should I include in a visual brief?
Name the subject, setting, visual style, lighting, and composition you want. Make requirements concrete, such as a red ceramic cup on a wooden table beside a window.
Start using FLUX.1 Kontext Max in Codex
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Codex:
set up https://spiral.ai/SKILL.md


