Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | nvidiaNVIDIA: SwitchyardRemove × | thinkingmachinesInkling-SmallRemove × | ideogramIdeogram V4.5 EditRemove × |
|---|---|---|---|
| What’s different | Switchyard is an open-source model router that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most popular... | Inkling-Small is a Mixture-of-Experts transformer with 276B total parameters, 12B active, trained on NVIDIA GB300 NVL72 systems. Like Inkling, it features native reasoning over audio and images, variable… | Mask-guided edits with a high-precision mode that restores unchanged pixels; combines a source image with extra references. |
| Date | Sep 21, 2026Listed | Jul 27, 2026Listed | Sep 30, 2026Listed |
API prices USD · provider configuration shown below | |||
| Listed rate | See provider quotes | $0.45 in / $1.20 out/ 1M tokensdeepinfra · via Hugging Face · all routes ↗ | See provider quotes |
| Provider endpoints | 1 endpoint → | 4 endpoints → | 0 endpoints → |
Specifications | |||
| Context window | 1M | 524.3K | — |
| Max output | — | 262.1K | — |
| Parameters | — | — | — |
| Tool calling | Not reported | Supported | Not reported |
| Structured output | Not reported | Supported | Not reported |
| Image input | Not reported | Supported | Not reported |
| Audio input | Not reported | Supported | Not reported |
| Reasoning | Not reported | Supported | Not reported |
| Prompt caching | Not reported | Supported | Not reported |
| Open weights | Not reported | Supported | Not reported |