How to Use GPT Image 2.5 Flare Edit in opencode
GPT Image 2.5 Flare Edit changes existing images while working to preserve subjects, composition, and visual style. Unlike GPT Image 2.5 Flare Text to Image, it starts from reference images for product edits, scene changes, and restyling.
Prompts to try with GPT Image 2.5 Flare Edit in opencode
Copy an example into opencode, or ask in your own words.
Use GPT Image 2.5 Flare Edit to revise the product photo in our assets folder. Replace only the background with pale stone; preserve the bottle shape, label, framing, and light direction. Return a 1024 × 1024 image.
Use GPT Image 2.5 Flare Edit on the existing onboarding illustration. Change only the orange objects to the project's green accent, preserving shapes and composition. Return a 1536 × 1024 PNG.
Remove the background from the photo I attach with GPT Image 2.5 Flare Edit and give me a transparent PNG. Save the result in ./assets.
Use GPT Image 2.5 Flare Edit to clean up these product shots so they sit on pure white.
Edit this image with GPT Image 2.5 Flare Edit: keep the subject, swap the background for a sunlit studio.
How to set up GPT Image 2.5 Flare Edit in opencode
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Leave out --global to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
- Sign in
Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, /mcps starts the same sign-in.
opencode mcp auth spiral
- Check it
Spiral shows as connected.
opencode mcp list
Use the Spiral skill
- Send opencode 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 GPT Image 2.5 Flare Edit
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": "openai/gpt-image-2.5/flare/edit", "input": { "prompt": "Same workers, same beam, same lunch boxes - but they'\''re all on their phones now. One is taking a selfie. One is on a call looking annoyed. Same danger, new…", "image_urls": [ "<image_urls>" ] } }'
Then paste one of the prompts above: opencode finds GPT Image 2.5 Flare Edit on Spiral, shows the price and runs it.
GPT Image 2.5 Flare Edit providers and prices
Spiral runs GPT Image 2.5 Flare Edit through fal and OpenAI. Open a card for today's price, with every fee included. Name one in your prompt, or let opencode pick.
$0.0475 per 4:3 image at high quality ($0.00572 low, $0.0122 medium, $0.084 xhigh, $0.188 max). At high: $0.0605 square, $0.069 square HD, $0.0342 16:9. Auto quality or size: the price of the one chosen for the request. Prompt: $6.50 per 1M tokens. Input images: $0.0106 each at 1024×1024.
$0.0686 per 1024×1024 image at high quality ($0.00775 low, $0.0172 medium, $0.122 xhigh, $0.274 max), plus each input image. At high: $0.0536 at 1536×1024 or 1024×1536, $0.0486 at 1792×1024 or 1024×1792, $0.0509 at 512×512, $0.0465 at 256×256. Auto quality or size: the price of the one chosen for the request. Prompt: $6.50 per 1M tokens. Input images: $0.0106 each at 1024×1024.
Settings you can ask for
GPT Image 2.5 Flare Edit works from your prompt, image URLs, and mask URL. Ask opencode for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Background | auto, transparent, or opaque | auto | Background for the generated image |
| Quality | auto, low, medium, high, xhigh, or max | high | Quality for the generated image. Higher settings increase detail, latency, and token usage. Use 'auto' to let the model choose. |
| Number of images | 1 to 10 | 1 | Number of images to generate |
| Output format | jpeg, png, or webp | png | Output format for the images |
| Output compression | 0 to 100 | Compression level from 0 to 100. Only supported when output_format is 'jpeg' or 'webp'. | |
| Image passthrough | on or off | off | Send reference images and masks without resizing or re-encoding, and return the provider's original image bytes and format. Requests use the direct OpenAI API. Masks must be PNGs with an alpha channel: transparent regions are edited, and dimensions must match the first reference. |
Every API field of GPT Image 2.5 Flare · Image Editing is on its tool page: open its card above.
What can you do with GPT Image 2.5 Flare Edit in opencode?
Turn project requirements into image assets and screen previews with GPT Image 2.5 Flare. A coding agent can use the project's design guidance to write briefs and check the resulting assets against their intended placement.
Social campaign visuals
Create a campaign scene from a written brief, or adapt an existing campaign image while preserving its main subject.
Editorial illustrations
Illustrate an article concept from text, or restyle an existing illustration with a specified palette and medium.
Interface previews
Explore screen layouts from a description, or revise an existing screen image. Review text and alignment before implementing the design.
Product scene concepts
Visualize a proposed product from a written description, or place an existing product image in a different setting.
Product background changes
Replace a product photo's setting while asking to preserve its shape, label, and camera angle.
Interior material previews
Change upholstery or finishes in an existing room photo, one change at a time, while retaining furniture placement.
Lighting studies
Compare daylight and evening treatments of an existing scene while asking to retain its objects and framing.
Reference-based restyling
Reinterpret a supplied subject in a different visual medium while checking that its identifying features remain recognizable.
GPT Image 2.5 Flare Edit success rate and speed on Spiral
Success and speed over the last 24 hours, across every run of these tools on Spiral.
| Tool | Success | Median time | Runs |
|---|---|---|---|
| GPT Image 2.5 Flare · Image Editing | 94.8% | 29.4s | 58 |
| GPT Image 2.5 Flare · Edit | Not enough runs | ||
More on GPT Image 2.5 Flare Edit and opencode
Overview
GPT Image 2.5 Flare Edit in other agents
Questions about GPT Image 2.5 Flare Edit in opencode
Can opencode use GPT Image 2.5 Flare Edit?
Yes. Add Spiral to opencode as an MCP server, and opencode can find and run GPT Image 2.5 Flare Edit like any built-in tool.
How much does GPT Image 2.5 Flare Edit cost in opencode?
$0.0475 per 4:3 image at high quality ($0.00572 low, $0.0122 medium, $0.084 xhigh, $0.188 max). At high: $0.0605 square, $0.069 square HD, $0.0342 16:9. Auto quality or size: the price of the one chosen for the request. Prompt: $6.50 per 1M tokens. Input images: $0.0106 each at 1024×1024. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your opencode plan is separate.
Do I need a fal account to use GPT Image 2.5 Flare Edit in opencode?
No. Spiral runs GPT Image 2.5 Flare Edit on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up GPT Image 2.5 Flare Edit in opencode?
About two minutes: add the server, then sign in, then check it.
Does opencode wait while GPT Image 2.5 Flare Edit runs?
GPT Image 2.5 Flare Edit runs in the background. opencode starts the run, checks on it and gives you the image when it's ready.
What is GPT Image 2.5 Flare good at?
Flare suits visual drafts for social content, product experiences, and image prototyping. Its strengths include natural lighting, textures, and following a defined visual style.
How large can GPT Image 2.5 Flare images be?
The longest edge can reach 3840 pixels, including 3840 × 2160 output. Dimensions must be multiples of 16, stay within a 3:1 aspect ratio, and total 655360 to 8294400 pixels; output above 2560 × 1440 is experimental.
Can GPT Image 2.5 Flare render readable text?
Yes, but exact placement and clarity can still fail. Put required wording in quotes, specify where it belongs, request no additional text, and check the result.
Can GPT Image 2.5 Flare create transparent images?
Yes. Request a transparent background with PNG or WebP output, then inspect edges and transparent areas before using the asset.
Does higher quality always improve GPT Image 2.5 Flare results?
No. Start with low quality for drafts, then compare higher settings against the specific detail or text problem you need to fix.
Start using GPT Image 2.5 Flare Edit in opencode
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into opencode:
set up https://spiral.ai/SKILL.md


