Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
| 1 model | thinkingmachinesInkling-SmallRemove × |
|---|---|
| What’s different | 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… |
| Date | Jul 27, 2026Listed |
API prices USD · provider configuration shown below | |
| Listed rate | $0.45 in / $1.20 out/ 1M tokensdeepinfra · via Hugging Face · all routes ↗ |
| Provider endpoints | 4 endpoints → |
Specifications | |
| Context window | 524.3K |
| Max output | 262.1K |
| Parameters | — |
| Tool calling | Supported |
| Structured output | Supported |
| Image input | Supported |
| Audio input | Supported |
| Reasoning | Supported |
| Prompt caching | Supported |
| Open weights | Supported |