[Integrations](https://spiral.ai/integrations) › [opencode](https://spiral.ai/integrations/opencode) › [GPT Image 2.6 Flare Text to Image](https://spiral.ai/integrations/opencode/gpt-image-2-6-flare-text-to-image)

# How to Use GPT Image 2.6 Flare Text to Image in opencode

GPT Image 2.6 Flare Text to Image creates posters, illustrations, and product concepts from a written brief. Unlike GPT Image 2.6 Flare Edit, it starts without a reference image, making it useful for exploring a new visual direction.

|  |  |
| --- | --- |
| Model | GPT Image 2.6 Flare Text to Image |
| Available through | fal |
| Category | Image |
| Price | $0.0473 per 4:3 image at high quality ($0.0224 low, $0.0391 medium, $0.0839 xhigh, $0.188 max). At high: $0.0603 square, $0.0689 square HD, $0.0341 16:9. Auto quality or size: the price of the one chosen for the request. Prompt: $6.50 per 1M tokens. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with GPT Image 2.6 Flare Text to Image in opencode

- Use GPT Image 2.6 Flare Text to Image to create a 1536 by 1024 illustration for the onboarding page, based on its copy in this project. Show a gardener sorting seeds into labeled envelopes, leave the right third open for page text, and include no lettering.
- Use GPT Image 2.6 Flare Text to Image to turn the README's three-step import process into a 1536 by 1024 diagram. Use the exact step names, large lettering, and left-to-right arrows; compare the result with the README before saving it.
- Use GPT Image 2.6 Flare Text to Image to create a 1024 by 1024 transparent PNG for the empty search state. Show a small illustrated mole examining a blank map, with no text; check that the output contains transparent pixels.
- Generate a product photo with GPT Image 2.6 Flare Text to Image: 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 GPT Image 2.6 Flare Text to Image.

## How to set up GPT Image 2.6 Flare Text to Image in opencode

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **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.

```bash
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
```

2. **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.

```bash
opencode mcp auth spiral
```

3. **Check it**: Spiral shows as connected.

```bash
opencode mcp list
```

### Use the Spiral skill

1. **Send opencode this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run GPT Image 2.6 Flare Text to Image**: One request; the result comes back by polling or a webhook.

```bash
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-2.6/flare/text-to-image",
    "input": {
      "prompt": "create a realistic image taken with iphone at these coordinates 41°43′32″N 49°56′49″W 15 April 1912"
    }
  }'
```

Then paste one of the prompts above: opencode finds GPT Image 2.6 Flare Text to Image on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/opencode

## GPT Image 2.6 Flare Text to Image tools and prices

- [GPT Image 2.6 Flare · Text to Image](https://spiral.ai/tools/fal/openai/gpt-image-2.6/flare/text-to-image) (fal): $0.0473 per 4:3 image at high quality ($0.0224 low, $0.0391 medium, $0.0839 xhigh, $0.188 max). At high: $0.0603 square, $0.0689 square HD, $0.0341 16:9. Auto quality or size: the price of the one chosen for the request. Prompt: $6.50 per 1M tokens.
- [GPT Image 2.6 Flare · Text to Image](https://spiral.ai/tools/openai/gpt-image-2.6-flare) (OpenAI): $0.0686 per 1024×1024 image at high quality ($0.0322 low, $0.0566 medium, $0.122 xhigh, $0.274 max). 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.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| image_size |  | landscape_4_3 | The size of the generated image. Supports preset names, explicit {width, height}, or 'auto' to let the model pick the best size. Concrete sizes must have both dimensions as multiples of 16, max edge 3840px, aspect ratio <= 3:1, total pixels between 655,360 and 8,294,400. |
| background | auto, transparent, opaque | auto | Background for the generated image |
| quality | auto, low, medium, high, xhigh, max | high | Quality for the generated image. Higher settings increase detail, latency, and token usage. Use 'auto' to let the model choose. |
| num_images | 1 to 10 | 1 | Number of images to generate |
| output_format | jpeg, png, 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'. |

## What can you do with GPT Image 2.6 Flare Text to Image in opencode?

Create visual assets alongside the code that uses them, including website illustrations and documentation graphics. Use project content to define the brief, then review lettering and composition before adding the image.

### Event posters

Create a poster from an event brief or revise an existing design. Specify the headline, date, and reading order, then proofread the result.

### Product campaign concepts

Explore a product scene from a written description or rework an existing product photo. Define the setting, lighting, and space needed for accompanying copy.

### Process diagrams

Draft a process graphic or revise an existing diagram using supplied steps and labels. Check every connection and label before sharing it.

### Editorial illustrations

Develop an illustration from an article brief or adapt existing artwork. Specify the subject, medium, palette, and intended crop.

### Original website illustrations

Turn a written feature description into an original illustration with a defined composition. Request a transparent background when the artwork needs to sit over a page surface.

### Presentation graphics

Generate a slide image from supplied content, with a clear headline and a small number of visual elements. Review text and relationships before adding it to a deck.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All opencode guides](https://spiral.ai/integrations/opencode)

## GPT Image 2.6 Flare Text to Image in other agents

- [Amp](https://spiral.ai/integrations/amp/gpt-image-2-6-flare-text-to-image)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/gpt-image-2-6-flare-text-to-image)
- [Claude](https://spiral.ai/integrations/claude-desktop/gpt-image-2-6-flare-text-to-image)
- [Claude Code](https://spiral.ai/integrations/claude-code/gpt-image-2-6-flare-text-to-image)
- [Cline](https://spiral.ai/integrations/cline/gpt-image-2-6-flare-text-to-image)
- [Codex](https://spiral.ai/integrations/codex/gpt-image-2-6-flare-text-to-image)
- [Cursor](https://spiral.ai/integrations/cursor/gpt-image-2-6-flare-text-to-image)
- [Devin](https://spiral.ai/integrations/devin/gpt-image-2-6-flare-text-to-image)
- [dots](https://spiral.ai/integrations/dots/gpt-image-2-6-flare-text-to-image)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/gpt-image-2-6-flare-text-to-image)
- [Gemini](https://spiral.ai/integrations/gemini/gpt-image-2-6-flare-text-to-image)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/gpt-image-2-6-flare-text-to-image)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/gpt-image-2-6-flare-text-to-image)
- [goose](https://spiral.ai/integrations/goose/gpt-image-2-6-flare-text-to-image)
- [Grok](https://spiral.ai/integrations/grok/gpt-image-2-6-flare-text-to-image)
- [Grok Build](https://spiral.ai/integrations/grok-build/gpt-image-2-6-flare-text-to-image)
- [Hermes](https://spiral.ai/integrations/hermes/gpt-image-2-6-flare-text-to-image)
- [Instinct](https://spiral.ai/integrations/instinct/gpt-image-2-6-flare-text-to-image)
- [Manus](https://spiral.ai/integrations/manus/gpt-image-2-6-flare-text-to-image)
- [Muse](https://spiral.ai/integrations/muse/gpt-image-2-6-flare-text-to-image)
- [Muse Code](https://spiral.ai/integrations/muse-code/gpt-image-2-6-flare-text-to-image)
- [n8n](https://spiral.ai/integrations/n8n/gpt-image-2-6-flare-text-to-image)
- [Notion](https://spiral.ai/integrations/notion/gpt-image-2-6-flare-text-to-image)
- [OpenClaw](https://spiral.ai/integrations/openclaw/gpt-image-2-6-flare-text-to-image)
- [Perplexity](https://spiral.ai/integrations/perplexity/gpt-image-2-6-flare-text-to-image)
- [Raycast](https://spiral.ai/integrations/raycast/gpt-image-2-6-flare-text-to-image)
- [VS Code](https://spiral.ai/integrations/vscode/gpt-image-2-6-flare-text-to-image)
- [Windsurf](https://spiral.ai/integrations/windsurf/gpt-image-2-6-flare-text-to-image)
- [Zapier](https://spiral.ai/integrations/zapier/gpt-image-2-6-flare-text-to-image)

## More opencode guides

- [GPT Image 2.6 Flare Edit](https://spiral.ai/integrations/opencode/gpt-image-2-6-flare-edit)
- [GPT Image 2.6 Sunburst](https://spiral.ai/integrations/opencode/gpt-image-2-6-sunburst)
- [GPT Image 2.5 Sunburst Text to Image](https://spiral.ai/integrations/opencode/gpt-image-2-5-sunburst-text-to-image)
- [GPT Image 2.6 Sunburst Edit](https://spiral.ai/integrations/opencode/gpt-image-2-6-sunburst-edit)
- [GPT Image 2.5 Sunburst Edit](https://spiral.ai/integrations/opencode/gpt-image-2-5-sunburst-edit)
- [GPT Image 2.6 Sunburst Text to Image](https://spiral.ai/integrations/opencode/gpt-image-2-6-sunburst-text-to-image)

## Questions about GPT Image 2.6 Flare Text to Image in opencode

**Can opencode use GPT Image 2.6 Flare Text to Image?**

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run GPT Image 2.6 Flare Text to Image like any built-in tool.

**How much does GPT Image 2.6 Flare Text to Image cost in opencode?**

$0.0473 per 4:3 image at high quality ($0.0224 low, $0.0391 medium, $0.0839 xhigh, $0.188 max). At high: $0.0603 square, $0.0689 square HD, $0.0341 16:9. Auto quality or size: the price of the one chosen for the request. Prompt: $6.50 per 1M tokens. 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 2.6 Flare Text to Image in opencode?**

No. Spiral runs GPT Image 2.6 Flare Text to Image 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 2.6 Flare Text to Image in opencode?**

About two minutes: add the server, then sign in, then check it.

**Does opencode wait while GPT Image 2.6 Flare Text to Image runs?**

GPT Image 2.6 Flare Text to Image runs in the background. opencode starts the run, checks on it and gives you the image when it's ready.

**What is GPT Image 2.6 Flare useful for?**

Use it to explore posters, product visuals, illustrations, and explanatory graphics. It suits workflows where you want to inspect a draft and refine the visual direction.

**How does Flare differ from Sunburst?**

Flare prioritizes faster iteration. Sunburst is designed for more demanding detail and precise edits, so compare their results on the details your work requires.

**Can GPT Image 2.6 Flare put readable text in an image?**

Yes, but spelling, clarity, and placement still need checking. Put the exact copy in quotation marks and specify where it belongs.

**How large can a still image be?**

The longest edge can reach 3840 pixels, with up to 8,294,400 total pixels. Both dimensions must be multiples of 16, the image must contain at least 655,360 pixels, and its proportions cannot exceed 3:1 in either direction.

**Can GPT Image 2.6 Flare make transparent assets?**

Yes. Use PNG or WebP and check the file's transparency rather than judging it from a preview alone.

