Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | googleGoogle: Gemini Embedding 2Remove × | intfloatmultilingual-e5-large-instructRemove × | ideogramIdeogram V4.5 Text to ImageRemove × |
|---|---|---|---|
| What’s different | Gemini Embedding 2 is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It… | The Multilingual-E5 models, initialized from XLM-RoBERTa, support up to 512 tokens per input — any longer text will be silently truncated. To ensure optimal performance, always prefix inputs with “query:”… | Generate high-quality images, posters, and logos with Ideogram 4.5, with accurate text rendering and low, medium, or high quality tiers. |
| Date | May 20, 2026Listed | Apr 17, 2025Listed | Sep 30, 2026Released |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.20 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ | See provider quotes | See provider quotes |
| Provider endpoints | 1 endpoint → | 0 endpoints → | 1 endpoint → |
Benchmarks Each result retains its evaluation configuration | |||
| AA Image ↗2.1 | Not reported | Not reported | 1,015.68 ↗Text-to-image · all categories · quality=highIndependent result95% CI 1,000.68–1,030.68 · n=2,634 |
Specifications | |||
| Context window | 8.2K | 512 | — |
| Max output | 7.4K | — | — |
| Parameters | — | — | — |
| Image input | Supported | Not reported | Not reported |
| Audio input | Supported | Not reported | Not reported |
| Video input | Supported | Not reported | Not reported |