Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | nvidiaNVIDIA-Nemotron-3.5-Super-VLRemove × | thinkingmachinesInkling-SmallRemove × |
|---|---|---|
| What’s different | NVIDIA Nemotron 3.5 Super VL is an open multimodal model for agents that see, reason, and act. Its 120B-parameter Mixture-of-Experts design (12B active) understands text, images, documents, GUIs, and video,… | 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 | Sep 16, 2026Listed | Jul 27, 2026Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | $0.10 in / $0.40 out/ 1M tokensDeepInfra · all routes ↗ | $0.45 in / $1.20 out/ 1M tokensdeepinfra · via Hugging Face · all routes ↗ |
| Provider endpoints | 7 endpoints → | 4 endpoints → |
Specifications | ||
| Context window | 1M | 524.3K |
| Max output | 235.9K | 262.1K |
| Parameters | — | — |
| Tool calling | Supported | Supported |
| Structured output | Supported | Supported |
| Image input | Supported | Supported |
| Audio input | Not reported | Supported |
| Video input | Supported | Not reported |
| Reasoning | Supported | Supported |
| Prompt caching | Supported | Supported |
| Open weights | Supported | Supported |