Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | openaiGPT Image 2.5 Flare Text to ImageRemove × | recraftRecraft V4.1 Flash Text to ImageRemove × |
|---|---|---|
| What’s different | General-purpose GPT Image 2.5 tier with transparent output, custom dimensions and five explicit quality levels. | Supply preferred RGB palette colors and a background color directly, alongside the text prompt and custom image dimensions. |
| Date | Sep 8, 2026Released | Sep 23, 2026Released |
API prices USD · provider configuration shown below | ||
| Listed rate | $30.00/ 1M output tokens + $5.00 / 1M text-input tokens · $8.00 / 1M image-input tokens OpenAI · via OpenRouter · Conditional | $0.007/ imagefal · all routes ↗ |
| Provider endpoints | 1 endpoint → | 2 endpoints → |
Benchmarks Each result retains its evaluation configuration | ||
| AA Image ↗2.1 | 1,206.72 ↗Text-to-image · all categories · quality=maxIndependent result95% CI 1,196.72–1,216.72 · n=12,364 | 949.34 ↗Text-to-image · all categoriesIndependent result95% CI 937.34–961.34 · n=5,770 |
Specifications | ||
| Context window | 400K | 65.5K |
| Max output | 360K | 59K |
| Parameters | — | — |
| Structured output | Supported | Not reported |
| Image input | Supported | Not reported |
| Prompt caching | Supported | Not reported |